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

    Neuronpedia

    INDEX
    Explanations

    needing more information

    np_max-act · gemini-2.0-flash

    This neuron detects phrases where the assistant asks to provide a more accurate (or helpful) response.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     payments
    -0.06
    股份
    -0.06
    Ky
    -0.06
    yx
    -0.06
     skl
    -0.06
    .ForeignKey
    -0.06
    (nr
    -0.06
    薩
    -0.06
    130
    -0.05
    _threshold
    -0.05
    POSITIVE LOGITS
    лемент
    0.07
    (QtGui
    0.07
     yık
    0.06
    .Visibility
    0.06
     SAC
    0.06
     noss
    0.06
     emblem
    0.06
     cerr
    0.06
     downloadable
    0.06
     locus
    0.06
    Act Density 0.023%

    No Known Activations