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

    Neuronpedia

    INDEX
    Explanations

    fear of vulnerability, failure, judgment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    δέ
    0.41
     සැල
    0.41
     _$
    0.39
    }"/>
    0.38
    oureux
    0.37
    ETTE
    0.37
    ேய
    0.37
    েয়
    0.36
    ेटा
    0.36
     हित
    0.35
    POSITIVE LOGITS
     confrontation
    0.91
     vulnerability
    0.79
     uncomfortable
    0.76
     confronting
    0.76
     discomfort
    0.74
     unfamiliar
    0.73
     embarrassment
    0.71
     confront
    0.71
     confrontations
    0.68
     scary
    0.66
    Act Density 0.038%

    No Known Activations