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

    Neuronpedia

    INDEX
    Explanations

    penetration testing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.61
     tl
    0.57
     April
    0.57
     May
    0.56
     Anthrop
    0.56
     scallop
    0.56
     spring
    0.55
     grapple
    0.54
     hun
    0.54
     Insulation
    0.54
    POSITIVE LOGITS
    éreo
    0.79
     ejecución
    0.75
     execução
    0.73
     состояния
    0.73
    મ
    0.71
     روی
    0.69
     средней
    0.67
     operações
    0.67
    ير
    0.66
     эффективности
    0.66
    Act Density 0.004%

    No Known Activations