Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    strings that end in "nen", "isto", "via", and "pel", but also selects shorter strings that look like parts of proper names.

    oai_token-act-pair · gemini-2.0-flash

    names or entities related to locations

    np_token-act-pair-logits · gpt-4o-mini

    Finnish topics and names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.79
    setVerticalGroup
    -0.74
    protoc
    -0.65
    StructEnd
    -0.65
     ddelweddau
    -0.63
    पया
    -0.62
    astify
    -0.61
     AssemblyCulture
    -0.59
    NgModule
    -0.59
     فريبيس
    -0.57
    POSITIVE LOGITS
     Thương
    0.46
    níků
    0.44
     Signalez
    0.42
     courir
    0.41
    atalyst
    0.41
     Kalt
    0.41
     bianche
    0.41
    時半
    0.41
    CopyWith
    0.40
    +#+
    0.40
    Act Density 0.176%

    No Known Activations