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

    Neuronpedia

    INDEX
    Explanations

    temperature

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of temperature conditions, especially the phrase “room temperature.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     창
    -0.07
    _SH
    -0.06
     منطقه
    -0.06
     imagen
    -0.06
     userType
    -0.06
     конца
    -0.06
    avourite
    -0.06
    织
    -0.06
    Directions
    -0.06
    _FATAL
    -0.06
    POSITIVE LOGITS
     Willis
    0.07
     parç
    0.07
     Malk
    0.06
     oil
    0.06
     aph
    0.06
     Labor
    0.06
    +c
    0.06
     rais
    0.06
    μ
    0.06
     mystery
    0.06
    Act Density 0.007%

    No Known Activations