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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pests
    -0.07
     tải
    -0.06
    ----------------------------------------------------------------
    -0.06
     shines
    -0.06
     python
    -0.06
     加
    -0.06
     Karma
    -0.06
     harmonic
    -0.06
    김
    -0.06
     dispute
    -0.06
    POSITIVE LOGITS
    .ViewModel
    0.07
     japon
    0.07
     polyline
    0.07
     trabal
    0.06
    976
    0.06
    obia
    0.06
     Venez
    0.06
    orThunk
    0.06
    "]));↵
    0.06
     Alphabet
    0.06
    Act Density 0.044%

    No Known Activations