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

    Neuronpedia

    INDEX
    Explanations

    So

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Philip
    -0.07
    Pressure
    -0.07
     яб
    -0.07
     поч
    -0.06
    开放
    -0.06
    448
    -0.06
    Ether
    -0.06
     Brun
    -0.06
     tiny
    -0.06
    -sum
    -0.06
    POSITIVE LOGITS
    /↵↵↵
    0.07
    _PROPERTY
    0.07
    ')}↵
    0.07
     USING
    0.07
     修
    0.07
    \system
    0.07
    \s
    0.07
    IVO
    0.06
     Spe
    0.06
    erves
    0.06
    Act Density 0.017%

    No Known Activations