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

    Neuronpedia

    INDEX
    Explanations

    Plank exercise

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     atrap
    0.87
    >>>>
    0.78
     avis
    0.75
    ී
    0.73
     jednak
    0.73
     boulder
    0.71
    FV
    0.70
     conhece
    0.69
     karne
    0.69
     indulge
    0.69
    POSITIVE LOGITS
    愆
    0.76
     Issue
    0.74
    CreateCharacter
    0.71
    PERATURE
    0.71
    otoxicity
    0.70
     Arabic
    0.69
    ançaise
    0.69
    ிஸ்த
    0.68
    பாடு
    0.68
    anı
    0.67
    Act Density 0.000%

    No Known Activations