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

    Neuronpedia

    INDEX
    Explanations

    alcohol and performance decline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    匱
    0.45
     scalability
    0.43
     assembled
    0.42
    ױ
    0.42
     semantic
    0.42
     generate
    0.41
    Semantic
    0.41
     Archiv
    0.40
     generated
    0.40
     cryptographic
    0.39
    POSITIVE LOGITS
     alcohol
    1.22
     Alcohol
    1.13
     drunk
    1.12
    Alcohol
    1.10
     алкого
    1.09
    alcohol
    1.09
     drunken
    1.09
     drunkenness
    1.05
    drunk
    1.02
     alkohol
    1.02
    Act Density 0.056%

    No Known Activations