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

    Neuronpedia

    INDEX
    Explanations

    payroll messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Plat
    0.37
     Kathmandu
    0.36
     tooth
    0.35
    rencies
    0.35
     ce
    0.34
     inflex
    0.34
     expl
    0.34
     क
    0.33
     harmonization
    0.33
     Based
    0.33
    POSITIVE LOGITS
    Sulf
    0.45
     विनाश
    0.45
    𒃲
    0.44
    毁灭
    0.43
    Fam
    0.43
     devast
    0.42
    .$\
    0.41
    feather
    0.41
     อื่น
    0.41
     devastated
    0.40
    Act Density 0.000%

    No Known Activations