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

    Neuronpedia

    INDEX
    Explanations

    );

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Composition
    -0.07
    ZH
    -0.07
    _est
    -0.07
    苏
    -0.07
    _mE
    -0.07
    better
    -0.06
    LLL
    -0.06
     Mayer
    -0.06
    _vars
    -0.06
    izards
    -0.06
    POSITIVE LOGITS
    ๐
    0.07
     علوم
    0.07
     кип
    0.07
     Generated
    0.06
     peers
    0.06
     minecraft
    0.06
     replica
    0.06
    Cong
    0.06
     очеред
    0.06
     secara
    0.06
    Act Density 0.007%

    No Known Activations