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

    Neuronpedia

    INDEX
    Explanations

    models and parameters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ابقه
    -0.08
     panties
    -0.07
     cutting
    -0.07
    cript
    -0.06
     стол
    -0.06
     감
    -0.06
     покуп
    -0.06
     coercion
    -0.06
     Superior
    -0.06
    +)/
    -0.06
    POSITIVE LOGITS
    kiye
    0.06
    .MessageBox
    0.06
    ﺘ
    0.06
     مربع
    0.06
    BAL
    0.06
    ford
    0.06
     instituted
    0.06
    -off
    0.06
     Jess
    0.06
    �
    0.06
    Act Density 0.146%

    No Known Activations