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

    Neuronpedia

    INDEX
    Explanations

    Hot

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the word “Hot” (in headings or as an adjective).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    358
    -0.07
     sieve
    -0.07
    stance
    -0.07
    PACE
    -0.07
     Rape
    -0.07
     Raven
    -0.07
    -case
    -0.06
    aida
    -0.06
    learn
    -0.06
     Lace
    -0.06
    POSITIVE LOGITS
     hot
    0.18
     Hot
    0.17
    Hot
    0.14
     HOT
    0.12
     hotspot
    0.11
    -hot
    0.11
    hot
    0.11
     hotline
    0.10
     hotter
    0.10
     hott
    0.09
    Act Density 0.011%

    No Known Activations