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

    Neuronpedia

    INDEX
    Explanations

    get

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    annonce
    -0.08
     случае
    -0.08
    莸
    -0.08
     hoog
    -0.07
    禋
    -0.07
     lié
    -0.07
    斩获
    -0.07
    اة
    -0.07
     playwright
    -0.07
    潆
    -0.07
    POSITIVE LOGITS
     Model
    0.06
    .Setter
    0.06
    (best
    0.06
    chemy
    0.06
     svensk
    0.06
    Ṣ
    0.06
     sketch
    0.06
    keletal
    0.06
    (Point
    0.06
    _SUPPORTED
    0.06
    Act Density 0.002%

    No Known Activations