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

    Neuronpedia

    INDEX
    Explanations

    chill

    np_max-act · gemini-2.0-flash

    The neuron fires strongly on words (and word fragments) that refer to cold or cooling (e.g. “cool,” “cold,” “kalt,” “차가운,” “Gefrier–”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ancement
    -0.07
    Jones
    -0.07
     oscillator
    -0.06
    405
    -0.06
     spherical
    -0.06
    op
    -0.06
     microphone
    -0.06
     antenna
    -0.06
     lcd
    -0.06
     Mutex
    -0.06
    POSITIVE LOGITS
     chilled
    0.08
     Cool
    0.07
     cool
    0.07
    berries
    0.07
     chill
    0.07
    명의
    0.07
    $IFn
    0.07
     이미
    0.07
     Jiří
    0.07
     ост
    0.06
    Act Density 0.026%

    No Known Activations