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

    Neuronpedia

    INDEX
    Explanations

    weak, inept, or negative traits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     robuste
    0.48
     robustness
    0.46
    艰
    0.43
     असामान्य
    0.43
    艱
    0.40
    Robust
    0.39
     defy
    0.39
     unheard
    0.39
     شہریوں
    0.38
     Robust
    0.37
    POSITIVE LOGITS
     incompetent
    0.98
     inept
    0.90
     opportunistic
    0.88
     greedy
    0.87
     opportun
    0.85
     manipulative
    0.82
     scheming
    0.81
     incompet
    0.80
     clueless
    0.80
     unreliable
    0.79
    Act Density 0.068%

    No Known Activations