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

    Neuronpedia

    INDEX
    Explanations

    control and increasingly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    T
    0.52
    sière
    0.47
    V
    0.46
    firefox
    0.44
    4
    0.42
    8
    0.42
    Infl
    0.41
    Vod
    0.40
    surgery
    0.40
    })}
    0.40
    POSITIVE LOGITS
     intensify
    0.53
     سعيد
    0.50
     obiettivo
    0.50
    uch
    0.50
     توقع
    0.49
     செய
    0.49
    ilas
    0.48
    áno
    0.46
     मर
    0.46
     پہلے
    0.45
    Act Density 0.001%

    No Known Activations