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

    Neuronpedia

    INDEX
    Explanations

    call home

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    セキュリティ
    0.82
     sicurezza
    0.81
     security
    0.79
     segurança
    0.79
     seguridad
    0.78
     보안
    0.78
    Security
    0.72
     امنیت
    0.72
    SECURITY
    0.71
     güvenlik
    0.71
    POSITIVE LOGITS
     Lending
    0.42
     Friday
    0.38
     charismatic
    0.38
     Lighthouse
    0.38
    အတ
    0.37
     L
    0.37
     Te
    0.36
     Net
    0.36
    rencies
    0.36
     SV
    0.35
    Act Density 0.001%

    No Known Activations