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

    Neuronpedia

    INDEX
    Explanations

    say "0"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dani
    -0.07
    нд
    -0.07
    쭝
    -0.07
    ↕
    -0.07
    ᕮ
    -0.07
    BeNull
    -0.07
    \GeneratedValue
    -0.07
    روم
    -0.06
    _pub
    -0.06
    (Self
    -0.06
    POSITIVE LOGITS
     teasing
    0.08
    	log
    0.07
    opport
    0.07
     tease
    0.07
    oca
    0.07
     harass
    0.06
     Cellular
    0.06
     disposition
    0.06
    销售渠道
    0.06
     authority
    0.06
    Act Density 0.032%

    No Known Activations