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

    Neuronpedia

    INDEX
    Explanations

    RTX graphics cards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    reciate
    0.69
     eigentlich
    0.67
     employees
    0.67
    従業
    0.64
     anthropologist
    0.64
    wunsch
    0.63
     człowieka
    0.63
     broadcasters
    0.63
    ienen
    0.63
    ונות
    0.62
    POSITIVE LOGITS
     செய்யப்பட்டு
    0.63
    {
    0.63
    reacted
    0.60
    р
    0.60
     થયું
    0.60
     შეიძ
    0.59
    expired
    0.59
    disk
    0.58
    panic
    0.57
     دارو
    0.57
    Act Density 0.005%

    No Known Activations