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

    Neuronpedia

    INDEX
    Explanations

    col

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Edwin
    -0.07
    อะ
    -0.07
    安
    -0.07
     потрап
    -0.07
     dün
    -0.06
    芳
    -0.06
     Brushes
    -0.06
    ères
    -0.06
     soldier
    -0.06
    強
    -0.06
    POSITIVE LOGITS
    γ
    0.07
    Γ
    0.07
    ยก
    0.07
    ynchron
    0.07
    ko
    0.06
     designs
    0.06
     وب
    0.06
    gon
    0.06
    col
    0.06
    ับส
    0.06
    Act Density 0.001%

    No Known Activations