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

    Neuronpedia

    INDEX
    Explanations

    protection and prevention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Unlock
    0.43
     Unlock
    0.40
     vezet
    0.40
     sublicense
    0.39
     trecut
    0.39
     überprüfen
    0.39
    جموعة
    0.38
     hochwertige
    0.38
    Via
    0.38
     স্মার্ট
    0.38
    POSITIVE LOGITS
     protection
    0.70
     protecting
    0.66
     보호
    0.66
     shielding
    0.64
     Protection
    0.63
     protects
    0.62
    保护
    0.61
     protect
    0.61
    保護
    0.61
    Protection
    0.58
    Act Density 0.125%

    No Known Activations