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

    Neuronpedia

    INDEX
    Explanations

    signing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    رسل
    -0.08
     filtering
    -0.08
     changing
    -0.08
     oli
    -0.08
    绕
    -0.07
    Cer
    -0.07
    орно
    -0.07
    OLS
    -0.07
    filtered
    -0.07
    ALI
    -0.07
    POSITIVE LOGITS
     precedence
    0.09
     تعاون
    0.09
     instit
    0.08
     перспектив
    0.08
     парт
    0.08
    iff
    0.08
     партнер
    0.08
     agreements
    0.08
    stakes
    0.08
     соглаш
    0.08
    Act Density 0.023%

    No Known Activations