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

    Neuronpedia

    INDEX
    Explanations

    references to environmental conditions, particularly snow and ice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ice and snow

    np_acts-logits-general · gemini-2.0-flash

    ice and snow states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cuero
    -0.53
    énario
    -0.51
     Huerta
    -0.48
     redwood
    -0.48
    ypep
    -0.46
     reflux
    -0.43
     epilepsy
    -0.43
     demurrer
    -0.43
    engah
    -0.43
    UAGES
    -0.43
    POSITIVE LOGITS
     ice
    2.08
     snow
    2.00
     Ice
    1.80
     Snow
    1.71
    Ice
    1.70
     frozen
    1.67
    Snow
    1.65
    snow
    1.64
     SNOW
    1.60
     thawed
    1.55
    Act Density 0.230%

    No Known Activations