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

    Neuronpedia

    INDEX
    Explanations

    al

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    둘
    -0.07
     bonds
    -0.07
    BEL
    -0.07
     Fill
    -0.07
    hora
    -0.07
     cardio
    -0.07
    <bool
    -0.06
    gage
    -0.06
     Form
    -0.06
     congen
    -0.06
    POSITIVE LOGITS
     места
    0.07
     plaintext
    0.07
     Jungle
    0.07
    صفقة
    0.07
     DataSource
    0.07
     ולכן
    0.07
    äsent
    0.07
     האתר
    0.07
    рат
    0.06
     Başkanı
    0.06
    Act Density 0.001%

    No Known Activations