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

    Neuronpedia

    INDEX
    Explanations

    development paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㴡
    0.49
    Requ
    0.46
     कश्मीर
    0.46
    ătur
    0.46
    াযোগ
    0.46
    कश्मीर
    0.46
    проек
    0.46
    罨
    0.46
     کمپیو
    0.46
    ırmak
    0.45
    POSITIVE LOGITS
     e
    0.58
     acab
    0.46
     формат
    0.42
     all
    0.42
    women
    0.41
     fascinated
    0.41
     engaged
    0.41
    ain
    0.40
    sharing
    0.40
     about
    0.40
    Act Density 0.000%

    No Known Activations