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

    Neuronpedia

    INDEX
    Explanations

    arrow icon, up, down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     circle
    0.87
     circles
    0.80
     Circle
    0.76
    圈
    0.73
     círculo
    0.73
    Circle
    0.72
     Circles
    0.70
    circles
    0.69
     cír
    0.68
    circle
    0.68
    POSITIVE LOGITS
    のこ
    0.42
    BLIC
    0.41
    eacute
    0.40
    Outline
    0.39
    ोलिक
    0.39
    Be
    0.37
    bert
    0.37
    szlig
    0.37
    boolean
    0.37
    agnetic
    0.36
    Act Density 0.000%

    No Known Activations