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

    Neuronpedia

    INDEX
    Explanations

    ary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ミ
    -0.07
     �
    -0.07
     Ambient
    -0.07
     branch
    -0.07
     Christoph
    -0.07
    ie
    -0.06
     �
    -0.06
    _Con
    -0.06
     С
    -0.06
     glimpse
    -0.06
    POSITIVE LOGITS
    (((
    0.08
    ayız
    0.07
     segregation
    0.06
    validated
    0.06
     Sey
    0.06
    ay
    0.06
    Essay
    0.06
     Dating
    0.06
    елення
    0.06
     Laundry
    0.06
    Act Density 0.001%

    No Known Activations