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

    Neuronpedia

    INDEX
    Explanations

    each every

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     اختر
    -0.08
     الخيار
    -0.07
    ก
    -0.07
     Wahl
    -0.07
     AR
    -0.07
     warped
    -0.07
     Triangle
    -0.07
    _threshold
    -0.07
     الأر
    -0.07
    _jump
    -0.07
    POSITIVE LOGITS
    everyone
    0.09
    INFRINGEMENT
    0.08
    iteach
    0.08
    פיק
    0.08
    उस
    0.08
     तयारी
    0.08
     तैयारी
    0.08
    ाधिक
    0.08
     assorted
    0.08
     सभी
    0.08
    Act Density 0.012%

    No Known Activations