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

    Neuronpedia

    INDEX
    Explanations

    Important considerations BEFORE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    L
    0.54
    ্স
    0.51
    ਈ
    0.49
    λ
    0.46
    ูก
    0.46
    க்
    0.46
    itions
    0.46
    린
    0.45
    A
    0.45
    도가
    0.44
    POSITIVE LOGITS
     (!)
    0.74
    (!)
    0.70
     ONLY
    0.58
     ძალიან
    0.58
    laublich
    0.58
    ❕
    0.57
    鏄
    0.57
    ຢູ່ໃນ
    0.56
     shockingly
    0.55
     sooo
    0.55
    Act Density 0.183%

    No Known Activations