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

    Neuronpedia

    INDEX
    Explanations

    orth

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     स
    -0.07
    lediği
    -0.07
    _DEAD
    -0.07
     mát
    -0.07
    Rows
    -0.06
     lasting
    -0.06
     нами
    -0.06
    hPa
    -0.06
    _variable
    -0.06
     Toshiba
    -0.06
    POSITIVE LOGITS
     Try
    0.07
    entreprise
    0.06
     ATH
    0.06
     Orth
    0.06
     Off
    0.06
     Psych
    0.06
     entreprise
    0.06
    企业
    0.06
    .…↵↵
    0.06
    -ref
    0.05
    Act Density 0.003%

    No Known Activations