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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Loc
    -0.06
     modeled
    -0.06
     ges
    -0.06
    는
    -0.06
     않았
    -0.06
    なら
    -0.06
    forward
    -0.06
    ΑΛ
    -0.06
     июня
    -0.06
     battle
    -0.06
    POSITIVE LOGITS
     Rohing
    0.08
    ahl
    0.07
    owntown
    0.07
     legalization
    0.07
     Intelli
    0.07
    .Ultra
    0.06
     fetisch
    0.06
     فن
    0.06
    atetime
    0.06
    微笑
    0.06
    Act Density 0.293%

    No Known Activations