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

    Neuronpedia

    INDEX
    Explanations

    left and next pointers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    内容的
    0.42
    痳
    0.42
     przech
    0.41
    きました
    0.41
    ไหล
    0.41
    诺
    0.41
    并
    0.40
     असून
    0.40
     cursorPos
    0.39
    プレート
    0.38
    POSITIVE LOGITS
    plan
    0.40
     هون
    0.39
    AK
    0.38
    planning
    0.38
    ubic
    0.38
    PLAN
    0.38
    llam
    0.37
    sec
    0.36
    razio
    0.36
    LB
    0.36
    Act Density 0.006%

    No Known Activations