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

    Neuronpedia

    INDEX
    Explanations

    writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    —with
    -0.07
     smashed
    -0.07
    不过
    -0.07
     Neville
    -0.06
     Heroes
    -0.06
    _CHARSET
    -0.06
    setMessage
    -0.06
    šší
    -0.06
     Jimmy
    -0.06
     forest
    -0.06
    POSITIVE LOGITS
    ulis
    0.07
     玩
    0.06
     internally
    0.06
     rootReducer
    0.06
     sequentially
    0.06
     errorCode
    0.06
    ρία
    0.06
    ays
    0.06
    測
    0.06
     Plug
    0.06
    Act Density 0.001%

    No Known Activations