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

    Neuronpedia

    INDEX
    Explanations

    ability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yard
    -0.07
     thugs
    -0.06
    .logging
    -0.06
    .Acc
    -0.06
     商
    -0.06
    .URI
    -0.06
     표
    -0.06
    enger
    -0.06
    νει
    -0.06
     anx
    -0.06
    POSITIVE LOGITS
     Programs
    0.06
    程序
    0.06
     makes
    0.06
    }><
    0.06
    یزات
    0.06
     rows
    0.06
     hypoc
    0.06
     jButton
    0.06
    -bottom
    0.06
     weakest
    0.06
    Act Density 0.254%

    No Known Activations