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
    (b
    -0.07
     mdl
    -0.07
    ◭
    -0.07
    ﱐ
    -0.07
    Img
    -0.07
     wzgl
    -0.07
     demanding
    -0.07
    わず
    -0.07
     exceeding
    -0.07
     supervisor
    -0.07
    POSITIVE LOGITS
    𝑺
    0.07
    AREST
    0.06
    配套
    0.06
    IGHT
    0.06
     AUG
    0.06
    簉
    0.06
    dictionary
    0.06
    _warnings
    0.06
    ﾏ
    0.06
    ordinated
    0.06
    Act Density 0.321%

    No Known Activations