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

    Neuronpedia

    INDEX
    Explanations

    search techniques

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of “search”‐related terms, spotting parts of the text that discuss searching or locating information.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     HttpResponse
    -0.08
    沟
    -0.06
     Replica
    -0.06
    -outs
    -0.06
     spectro
    -0.06
    Ill
    -0.06
    む
    -0.06
    -fashion
    -0.06
    _lcd
    -0.06
    Button
    -0.06
    POSITIVE LOGITS
     řed
    0.07
     الانت
    0.07
     Ticaret
    0.06
    [--
    0.06
    uppy
    0.06
    ephir
    0.06
     Lesser
    0.06
     revoked
    0.06
    _BOTTOM
    0.06
     亚
    0.06
    Act Density 0.132%

    No Known Activations