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

    Neuronpedia

    INDEX
    Explanations

    curve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     taş
    -0.07
     neler
    -0.06
    Content
    -0.06
     Protective
    -0.06
     vergi
    -0.06
     nichž
    -0.06
    考试
    -0.06
     řada
    -0.06
     chores
    -0.06
     PhD
    -0.06
    POSITIVE LOGITS
     irq
    0.07
     blogger
    0.07
    elle
    0.06
    ैश
    0.06
    efs
    0.06
     stirred
    0.06
    تغ
    0.06
    �
    0.06
    Tap
    0.06
    SSERT
    0.06
    Act Density 0.046%

    No Known Activations