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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Б
    -0.07
     Reputation
    -0.07
    �
    -0.06
     😉↵↵
    -0.06
    YN
    -0.06
     �
    -0.06
    ือน
    -0.06
     Bur
    -0.06
    uated
    -0.06
                           ↵
    -0.06
    POSITIVE LOGITS
    ерина
    0.07
     Verification
    0.07
    GreaterThan
    0.07
    prend
    0.07
    rtle
    0.07
     weakSelf
    0.07
    atchet
    0.07
     everything
    0.06
     interacting
    0.06
    ника
    0.06
    Act Density 0.000%

    No Known Activations