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

    Neuronpedia

    INDEX
    Explanations

    angle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onest
    -0.07
     fsm
    -0.06
    .Restr
    -0.06
     skirt
    -0.06
     اختیار
    -0.06
     آتش
    -0.06
    ひと
    -0.06
    open
    -0.06
     tong
    -0.06
    毛
    -0.06
    POSITIVE LOGITS
     خصوص
    0.07
     nabí
    0.07
    _UPLOAD
    0.07
     unexpected
    0.07
     elekt
    0.06
     autop
    0.06
     compatibility
    0.06
     neuken
    0.06
    addAction
    0.06
    _COMPAT
    0.06
    Act Density 0.012%

    No Known Activations