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

    Neuronpedia

    INDEX
    Explanations

    even share

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hordes
    0.65
     specs
    0.64
     shirt
    0.59
     monstros
    0.59
     lasts
    0.58
     dura
    0.58
     all
    0.58
     duro
    0.58
     horde
    0.57
     suit
    0.57
    POSITIVE LOGITS
    Admin
    0.75
    Provide
    0.75
    Information
    0.73
    Learning
    0.73
    Thông
    0.73
     Органи
    0.72
    Evaluating
    0.72
    Pokud
    0.72
    Điều
    0.71
    Marketing
    0.71
    Act Density 14.379%

    No Known Activations