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

    Neuronpedia

    INDEX
    Explanations

    stop loss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onaut
    -0.08
    CompanyId
    -0.08
    -boy
    -0.07
     Guantanamo
    -0.07
    파트
    -0.07
    SET
    -0.07
    лений
    -0.06
    사이
    -0.06
    Interaction
    -0.06
     tempt
    -0.06
    POSITIVE LOGITS
    cols
    0.07
     cooler
    0.06
     Ок
    0.06
     rules
    0.06
    ski
    0.06
     Seit
    0.06
     Estr
    0.06
    aly
    0.06
     bookmarks
    0.06
     these
    0.06
    Act Density 0.006%

    No Known Activations