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

    Neuronpedia

    INDEX
    Explanations

    prior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Game
    -0.08
    Game
    -0.08
    UGC
    -0.07
    channels
    -0.07
     گ
    -0.07
     аллерг
    -0.07
    .:.:.:.:
    -0.07
    }&
    -0.07
     맥
    -0.07
     clumsy
    -0.07
    POSITIVE LOGITS
     prior
    0.18
     Prior
    0.15
    Prior
    0.15
    prior
    0.11
    rior
    0.10
     pir
    0.09
    iar
    0.08
    pri
    0.08
    ir
    0.08
     patri
    0.08
    Act Density 0.011%

    No Known Activations