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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     infusion
    -0.07
    tl
    -0.07
    ith
    -0.07
     ml
    -0.06
     kr
    -0.06
     vanish
    -0.06
    سل
    -0.06
    θος
    -0.06
    629
    -0.06
    endir
    -0.06
    POSITIVE LOGITS
     almond
    0.06
    <Value
    0.06
     вой
    0.06
     cevap
    0.06
     λέ
    0.06
    (Double
    0.06
    Screen
    0.06
    ̂
    0.06
    ique
    0.06
    梅
    0.06
    Act Density 0.097%

    No Known Activations