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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    065
    -0.06
    Alg
    -0.06
    Nota
    -0.06
     hỗn
    -0.06
    ाएग
    -0.06
    .quality
    -0.06
    drink
    -0.06
    .ToString
    -0.06
    ////////////////////////////////////////////////////////////////////////////
    -0.06
    折
    -0.06
    POSITIVE LOGITS
    .splitext
    0.07
     getX
    0.07
    adients
    0.06
     ferry
    0.06
    .useState
    0.06
    ANO
    0.06
    松
    0.06
     recreated
    0.06
    metatable
    0.06
     ideological
    0.06
    Act Density 0.003%

    No Known Activations