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

    Neuronpedia

    INDEX
    Explanations

    references to examples or instructions in technical content

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

    actions and modifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FailureListener
    -0.48
     Bisnis
    -0.40
    ksamkeit
    -0.39
    tonode
    -0.37
     kağıdı
    -0.35
     themſelves
    -0.35
     Norvège
    -0.35
     cantons
    -0.35
    seguida
    -0.34
     Beſ
    -0.34
    POSITIVE LOGITS
    OGND
    0.54
     snippetHide
    0.53
     AssemblyCulture
    0.50
    Rhestr
    0.49
    Hentet
    0.48
     <>",
    0.48
    oneofs
    0.47
     Signalez
    0.47
    AndEndTag
    0.47
    Autoritní
    0.46
    Act Density 0.128%

    No Known Activations