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

    Neuronpedia

    INDEX
    Explanations

    being affected or vulnerable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nu
    0.42
    appropriate
    0.42
    backed
    0.42
    nel
    0.41
    ip
    0.40
    nl
    0.40
    arounds
    0.39
    required
    0.39
    approved
    0.39
    approval
    0.39
    POSITIVE LOGITS
     by
    0.59
    จาก
    0.48
     affected
    0.46
    จากการ
    0.46
     of
    0.46
     متاثر
    0.45
     Affected
    0.44
     oleh
    0.44
    នៃ
    0.44
     чрез
    0.43
    Act Density 0.090%

    No Known Activations