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

    Neuronpedia

    INDEX
    Explanations

    how intense or serious

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     handleClick
    0.54
     крово
    0.54
     вакци
    0.53
    ה
    0.53
    ఞ
    0.51
    лли
    0.49
     ૧
    0.48
    0.48
     precluded
    0.48
     세제곱
    0.48
    POSITIVE LOGITS
    rail
    0.49
    4
    0.47
    voi
    0.47
    dam
    0.46
     Zu
    0.45
    roads
    0.45
    rys
    0.45
    weisen
    0.44
    7
    0.44
     tertentu
    0.44
    Act Density 0.002%

    No Known Activations