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

    Neuronpedia

    INDEX
    Explanations

    protection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isia
    -0.06
    ffect
    -0.06
    IMPLIED
    -0.06
     ignorant
    -0.06
    	td
    -0.06
     Âu
    -0.06
    apat
    -0.06
    ีป
    -0.06
    orro
    -0.05
    سط
    -0.05
    POSITIVE LOGITS
     NIR
    0.07
    checking
    0.07
    qm
    0.07
     الشركة
    0.07
    _verified
    0.06
     Officials
    0.06
    ीआई
    0.06
     landscaping
    0.06
    Available
    0.06
    )v
    0.06
    Act Density 0.007%

    No Known Activations