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

    Neuronpedia

    INDEX
    Explanations

    a variety of seemingly unrelated content including code snippets, prices, and references to hot food

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TextAppearance
    -0.55
     propOrder
    -0.51
     originais
    -0.50
    COMMERCIAL
    -0.49
     AsyncTask
    -0.46
    ️⃣
    -0.45
     lidí
    -0.45
    TestingModule
    -0.45
    .³
    -0.44
     zwierząt
    -0.44
    POSITIVE LOGITS
    ването
    0.60
    __(/*!
    0.60
    //
    0.60
     nahilalakip
    0.59
    вање
    0.59
    ъм
    0.58
    matchCondition
    0.57
     Belong
    0.57
     setw
    0.57
    endcsname
    0.57
    Act Density 1.530%

    No Known Activations