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

    Neuronpedia

    INDEX
    Explanations

    relationship

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     інозем
    -0.06
     Those
    -0.06
     vodka
    -0.06
     Mex
    -0.06
     هیچ
    -0.06
     jedním
    -0.06
     Zag
    -0.06
     Bunifu
    -0.06
     высок
    -0.06
     canine
    -0.06
    POSITIVE LOGITS
     xor
    0.07
    (range
    0.07
     emergencies
    0.07
     ----------↵
    0.07
    pon
    0.07
    _discount
    0.07
     strategies
    0.06
     Investing
    0.06
    game
    0.06
    (dep
    0.06
    Act Density 0.003%

    No Known Activations