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

    Neuronpedia

    INDEX
    Explanations

    academic writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сила
    -0.07
    파일
    -0.06
    nilai
    -0.06
    malıdır
    -0.06
    surface
    -0.06
    Capital
    -0.06
    carrier
    -0.06
    mathrm
    -0.06
    ्टर
    -0.06
    ώνα
    -0.06
    POSITIVE LOGITS
    ooth
    0.06
     for
    0.06
     how
    0.06
     perme
    0.06
     comedian
    0.06
     hastily
    0.06
     Lager
    0.06
     Assignment
    0.06
    .robot
    0.06
     useForm
    0.06
    Act Density 0.520%

    No Known Activations