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

    Neuronpedia

    INDEX
    Explanations

    ignoring or neglecting issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     어려
    0.46
     Uncertain
    0.45
     infusions
    0.45
     Purposes
    0.44
     pears
    0.44
    avy
    0.41
    ױ
    0.40
     Alone
    0.40
     OF
    0.40
    illerie
    0.40
    POSITIVE LOGITS
     neglect
    1.16
    無視
    1.03
     ignore
    1.02
     ignored
    0.97
     neglected
    0.96
     neglects
    0.93
    忽略
    0.89
     négl
    0.86
     ignores
    0.86
     Ignoring
    0.85
    Act Density 0.050%

    No Known Activations