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
     exe
    -0.08
    做工
    -0.07
     joke
    -0.07
     איכותי
    -0.07
    එ
    -0.07
    OPT
    -0.07
    Pure
    -0.07
     victory
    -0.07
    /respond
    -0.07
    /D
    -0.07
    POSITIVE LOGITS
    (express
    0.08
    已经达到
    0.08
    _GUID
    0.07
     alignSelf
    0.07
     FIN
    0.07
    左手
    0.07
    먹
    0.06
     rollers
    0.06
     Abdul
    0.06
    ↿
    0.06
    Act Density 0.045%

    No Known Activations