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

    Neuronpedia

    INDEX
    Explanations

    self-protection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rä
    0.89
    வ்வேறு
    0.86
    শনাল
    0.85
     Ramona
    0.85
     Femin
    0.84
     Código
    0.83
     Mga
    0.83
     So
    0.82
     Çünkü
    0.81
     Mahatma
    0.80
    POSITIVE LOGITS
    });
    0.85
    vector
    0.72
    ל
    0.71
    веси
    0.70
    cycline
    0.68
    }');
    0.68
    ellite
    0.66
    isent
    0.66
    mandatory
    0.66
    s
    0.66
    Act Density 0.002%

    No Known Activations