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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by grades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    前に
    0.40
    Capacity
    0.40
    owal
    0.39
     haloes
    0.38
    Licenses
    0.38
    रज
    0.37
    有限
    0.36
    盱
    0.36
    HTTP
    0.36
    容量
    0.35
    POSITIVE LOGITS
     remaining
    0.54
     Remaining
    0.53
    remaining
    0.52
     এরপর
    0.49
    剩下的
    0.48
    এরপর
    0.45
     сразу
    0.42
     Setelah
    0.42
     resuming
    0.42
     leftover
    0.41
    Act Density 0.073%

    No Known Activations