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

    Neuronpedia

    INDEX
    Explanations

    bulletproof vests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     outras
    0.56
     lésions
    0.55
     cull
    0.54
    кина
    0.53
     minhas
    0.53
     другими
    0.53
     confiança
    0.53
     нама
    0.53
     comércio
    0.53
     cafe
    0.52
    POSITIVE LOGITS
    =
    0.62
    Poor
    0.57
    Thunder
    0.56
    Sock
    0.54
     Poor
    0.52
    洞
    0.52
    Airport
    0.50
    Healthy
    0.49
    oor
    0.48
     Airport
    0.48
    Act Density 0.000%

    No Known Activations