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

    Neuronpedia

    INDEX
    Explanations

    ag

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     методи
    -0.06
     commodo
    -0.06
     disposit
    -0.06
    here
    -0.06
    readcrumbs
    -0.06
    modelName
    -0.06
    ि,
    -0.06
    ell
    -0.06
     geliştir
    -0.05
     vim
    -0.05
    POSITIVE LOGITS
     Se
    0.08
    alex
    0.07
     strawberries
    0.06
    Se
    0.06
     northwest
    0.06
     Frequency
    0.06
    εξ
    0.06
     dwelling
    0.06
     价格
    0.06
     separate
    0.06
    Act Density 0.003%

    No Known Activations