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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     öne
    -0.08
    -any
    -0.07
    strate
    -0.06
     标
    -0.06
    童
    -0.06
     bước
    -0.06
     finance
    -0.06
     <!--<
    -0.06
    -Fi
    -0.06
     Pocket
    -0.06
    POSITIVE LOGITS
     shoot
    0.07
    ur
    0.06
     DERP
    0.06
     full
    0.06
    icken
    0.06
    .Bool
    0.06
    ListView
    0.06
     meaning
    0.06
    ję
    0.05
     Kardashian
    0.05
    Act Density 0.038%

    No Known Activations