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

    Neuronpedia

    INDEX
    Explanations

    code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ID
    -0.07
    ρεί
    -0.06
     mouth
    -0.06
     diver
    -0.06
     behind
    -0.06
    fü
    -0.06
    هور
    -0.06
    fox
    -0.06
    ordes
    -0.06
     цьому
    -0.06
    POSITIVE LOGITS
    sequelize
    0.06
     gifts
    0.06
     opět
    0.06
     ABD
    0.06
    CallableWrapper
    0.06
     babes
    0.06
     Milky
    0.06
    (Page
    0.06
     conducts
    0.06
    .onViewCreated
    0.06
    Act Density 0.004%

    No Known Activations