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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     सर्वो
    -0.08
     roots
    -0.08
    myp
    -0.08
     rulers
    -0.07
     nuclear
    -0.07
     crushers
    -0.07
     direita
    -0.07
     indicators
    -0.07
     को
    -0.07
     बाज
    -0.07
    POSITIVE LOGITS
    Throws
    0.09
     (!)
    0.09
     necessariamente
    0.09
     necesariamente
    0.09
    ，否则
    0.08
     forcément
    0.08
    才能
    0.08
    不存在
    0.08
     Throws
    0.08
     обязательно
    0.08
    Act Density 0.021%

    No Known Activations