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

    Neuronpedia

    INDEX
    Explanations

    phase

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of “phase” (and its inflected forms, e.g. “phases,” “phase transition”) in scientific text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    쿠
    -0.07
     Diff
    -0.07
     Knoxville
    -0.06
    438
    -0.06
    Carthy
    -0.06
    TU
    -0.06
     گن
    -0.06
    437
    -0.06
    ительства
    -0.06
    Couldn
    -0.06
    POSITIVE LOGITS
     Group
    0.07
     ath
    0.07
    formerly
    0.07
    	sizeof
    0.07
     misconduct
    0.06
     placer
    0.06
    _global
    0.06
     disple
    0.06
     affirm
    0.06
    _invite
    0.06
    Act Density 0.003%

    No Known Activations