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

    Neuronpedia

    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    овані
    -0.06
     deben
    -0.06
    (Filter
    -0.06
     kvinnor
    -0.06
    TabIndex
    -0.06
     подключ
    -0.06
    licher
    -0.06
     besteht
    -0.06
    واج
    -0.06
     získat
    -0.06
    POSITIVE LOGITS
    "s
    0.08
     kidn
    0.07
     ゝ
    0.07
    s
    0.07
    sky
    0.07
    NR
    0.06
     рис
    0.06
     ثلاث
    0.06
    لاث
    0.06
    "]]
    0.06
    Act Density 0.004%

    No Known Activations