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

    Neuronpedia

    INDEX
    Explanations

    recipes and instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ration
    -0.09
    NJ
    -0.08
    igest
    -0.08
     coefficients
    -0.08
    Coefficient
    -0.07
     modulus
    -0.07
    Coef
    -0.07
    Reduction
    -0.07
     attempt
    -0.07
    adie
    -0.07
    POSITIVE LOGITS
     salads
    0.09
     invigor
    0.08
     salad
    0.08
    validator
    0.08
    学生
    0.08
    点
    0.08
    .nodes
    0.08
     liefern
    0.08
    나
    0.08
     mắt
    0.08
    Act Density 0.022%

    No Known Activations