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

    Neuronpedia

    INDEX
    Explanations

    adverbs indicating frequency or extent of use

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

    how something is applied or used

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     this
    -0.49
    this
    -0.48
     that
    -0.44
    that
    -0.43
     rempliss
    -0.43
     ouv
    -0.42
    the
    -0.42
     it
    -0.42
     nemlig
    -0.41
    The
    -0.41
    POSITIVE LOGITS
    CppMethod
    0.87
     <<<<<<<<<<<<<<
    0.84
    featureID
    0.83
    IsMutable
    0.78
     ivelany
    0.77
    WriteTagHelper
    0.77
     $_(
    0.75
     мәкал
    0.73
    ſicht
    0.73
     blevet
    0.73
    Act Density 0.106%

    No Known Activations