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

    Neuronpedia

    INDEX
    Explanations

    trusting self or instincts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NotFound
    0.95
     поги
    0.94
    gher
    0.93
     맞
    0.88
     হা
    0.87
     revenge
    0.86
    acz
    0.86
     resented
    0.86
    د
    0.86
    determine
    0.85
    POSITIVE LOGITS
     trusting
    1.74
     trust
    1.60
    Trust
    1.59
     Trust
    1.50
     trusts
    1.47
     confiar
    1.41
    trust
    1.41
     confiance
    1.31
     വിശ്വാ
    1.30
     fiducia
    1.25
    Act Density 0.081%

    No Known Activations