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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ending in common suffixes

    np_acts-logits-general · gemini-2.0-flash

    responsiveness, epiphanies, panmixia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.53
    ×
    -0.51
     Supervisory
    -0.51
    }}^{\
    -0.50
    ']));
    -0.49
    CPtr
    -0.49
    upu
    -0.48
    kovsky
    -0.48
    inske
    -0.48
    })}
    -0.47
    POSITIVE LOGITS
    NUMX
    0.85
     للمعارف
    0.77
    uxxxx
    0.77
    URLException
    0.76
    AnimationsModule
    0.73
    orianCalendar
    0.66
     estekak
    0.63
    expandindo
    0.61
    ttino
    0.61
     InputDecoration
    0.60
    Act Density 0.378%

    No Known Activations