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

    Neuronpedia

    INDEX
    Explanations

    claims/statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ё
    -0.06
    전히
    -0.06
    في
    -0.06
     другие
    -0.06
    PIN
    -0.06
     ноги
    -0.06
    CAT
    -0.06
    Ya
    -0.06
    WG
    -0.06
    _ts
    -0.06
    POSITIVE LOGITS
     Splash
    0.06
    ges
    0.06
     junit
    0.06
     amused
    0.06
     emission
    0.06
    _POLICY
    0.06
    _PAYMENT
    0.06
     queen
    0.06
     invited
    0.06
    .Results
    0.06
    Act Density 0.105%

    No Known Activations