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

    Neuronpedia

    INDEX
    Explanations

    words related to coma and its effects

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

    coma recovery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.60
    GINIA
    -0.50
     Psi
    -0.46
     Stro
    -0.46
     Stron
    -0.44
     indisponible
    -0.44
    anical
    -0.40
     Security
    -0.40
    Тру
    -0.40
    cipline
    -0.40
    POSITIVE LOGITS
     comet
    2.23
     Comet
    2.14
    Comet
    2.08
     comets
    1.84
    comet
    1.80
    彗
    1.18
     kome
    0.85
     Kome
    0.82
     Come
    0.81
     meteor
    0.77
    Act Density 0.003%

    No Known Activations