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

    Neuronpedia

    INDEX
    Explanations

    GUI code, window size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (suite
    -0.07
    /animate
    -0.07
     بل
    -0.07
     Shame
    -0.07
     fanc
    -0.07
     zb
    -0.07
     Comes
    -0.07
     mess
    -0.07
    薹
    -0.07
    _SAMPLE
    -0.07
    POSITIVE LOGITS
     perfor
    0.08
    UpEdit
    0.07
     Unsure
    0.07
    ayan
    0.06
     ByteArrayOutputStream
    0.06
     Ha
    0.06
    Perfil
    0.06
    çois
    0.06
    HS
    0.06
    وار
    0.06
    Act Density 0.009%

    No Known Activations