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

    Neuronpedia

    INDEX
    Explanations

    special characters and programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     IDS
    0.95
     VLAN
    0.90
     Poincaré
    0.87
     criar
    0.86
     UIScrollView
    0.86
    CONFLICT
    0.86
     Gestión
    0.85
     hernia
    0.84
     UIS
    0.84
     desenhos
    0.83
    POSITIVE LOGITS
    ри
    0.93
    rc
    0.84
    서
    0.83
    єте
    0.77
    unque
    0.76
    риф
    0.75
    נדי
    0.75
    ди
    0.75
     сприя
    0.72
    인
    0.72
    Act Density 0.001%

    No Known Activations