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

    Neuronpedia

    INDEX
    Explanations

    protection from or of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     frmt
    0.43
     hỗ
    0.43
     pripad
    0.41
     आइकॉन
    0.40
     oprav
    0.38
     Admit
    0.38
     एडमिट
    0.38
    ត្
    0.38
     onBackPressed
    0.38
    ான்
    0.38
    POSITIVE LOGITS
     protecting
    0.98
     protect
    0.97
     protects
    0.94
     protector
    0.91
     prote
    0.88
    保护
    0.88
     Protect
    0.86
     protected
    0.85
     against
    0.83
     保護
    0.82
    Act Density 0.015%

    No Known Activations