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

    Neuronpedia

    INDEX
    Explanations

    words describing spatial relationships or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    prepositions of location or direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     matters
    -0.41
     ducks
    -0.41
     Matters
    -0.39
     doings
    -0.38
    ContentAsync
    -0.38
     cares
    -0.38
     song
    -0.37
     going
    -0.37
    bacher
    -0.37
    maschine
    -0.36
    POSITIVE LOGITS
    IndentedString
    0.73
    Autoritní
    0.65
     CreateTagHelper
    0.63
    IUrlHelper
    0.60
     betweenstory
    0.59
    Tembelea
    0.59
     snippetHide
    0.56
    脚注の使い方
    0.56
    principalTable
    0.53
    StructEnd
    0.52
    Act Density 0.078%

    No Known Activations