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

    Neuronpedia

    INDEX
    Explanations

    creation and decline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     metr
    0.41
     enroll
    0.40
    கு
    0.40
     โรง
    0.39
    slot
    0.39
     ਕਰੋ
    0.39
     标准
    0.38
     स्ल
    0.38
     slot
    0.38
    賭
    0.38
    POSITIVE LOGITS
     COMM
    0.38
    COMM
    0.38
    삵
    0.37
     Cab
    0.37
    Civ
    0.37
    Comm
    0.36
    Signal
    0.36
    AppDelegate
    0.35
    Cab
    0.35
    WebKit
    0.35
    Act Density 0.000%

    No Known Activations