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

    Neuronpedia

    INDEX
    Explanations

    making sense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lias
    -0.36
     VIA
    -0.27
    ÑģÑĤой
    -0.27
    èĪĮ
    -0.26
     Bra
    -0.26
    etri
    -0.25
    éĿĴæĺ¥
    -0.24
    nika
    -0.24
    chal
    -0.24
    chrift
    -0.24
    POSITIVE LOGITS
    ransition
    0.29
    PLIC
    0.26
    uel
    0.26
    olest
    0.26
    è¯ī
    0.25
    ино
    0.25
    por
    0.24
    ScreenState
    0.24
     Beit
    0.24
    交ç»ĩ
    0.24
    Act Density 0.003%

    No Known Activations