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

    Neuronpedia

    INDEX
    Explanations

    superlative adjectives and ordinal numbers

    oai_token-act-pair · gemini-2.0-flash

    terms related to firsts or notable mentions

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

    beginnings or main components

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     als
    -0.40
    only
    -0.36
    sed
    -0.36
    於
    -0.36
     tr
    -0.35
    yarnpkg
    -0.35
     Only
    -0.35
    ,
    -0.35
     din
    -0.35
     kaynağından
    -0.34
    POSITIVE LOGITS
     itſelf
    0.87
     requirement
    0.84
     pleaſure
    0.82
     thing
    0.81
     numberWith
    0.79
    requirement
    0.78
     resourceCulture
    0.77
     mistake
    0.75
     ingredient
    0.75
     ſtate
    0.75
    Act Density 2.357%

    No Known Activations