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

    Neuronpedia

    INDEX
    Explanations

    inherent weakness or fragility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     occasionally
    0.79
     oppure
    0.77
     nominations
    0.74
     বক্তৃতা
    0.72
     opiniones
    0.71
     gustaría
    0.71
     ぐらい
    0.68
     newsletters
    0.66
     alcuni
    0.66
     polémica
    0.65
    POSITIVE LOGITS
     fragility
    0.96
    脆弱
    0.88
     fragile
    0.87
     imperme
    0.86
     susceptibility
    0.84
     vulnerability
    0.81
     inherently
    0.80
     свойства
    0.80
    特殊
    0.79
     brittle
    0.79
    Act Density 0.000%

    No Known Activations