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

    Neuronpedia

    INDEX
    Explanations

    original

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stature
    -0.07
     Ung
    -0.07
    -la
    -0.07
    POINT
    -0.06
    僅
    -0.06
     Mun
    -0.06
     notable
    -0.06
    .number
    -0.06
     programmers
    -0.06
    ा
    -0.06
    POSITIVE LOGITS
    real
    0.06
     parent
    0.06
    Init
    0.06
    //****************************************************************************
    0.06
     alignments
    0.06
     پوش
    0.06
    acteria
    0.06
    ่อย
    0.06
    ساس
    0.06
     Montreal
    0.06
    Act Density 0.008%

    No Known Activations