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

    Neuronpedia

    INDEX
    Explanations

    research aims

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     streak
    -0.07
    Ky
    -0.07
     sabe
    -0.07
     Θε
    -0.07
     Koch
    -0.06
     mesmo
    -0.06
     Month
    -0.06
     REVIEW
    -0.06
    取消
    -0.06
     minimizing
    -0.06
    POSITIVE LOGITS
    (ml
    0.07
    dro
    0.07
    ін
    0.06
    =
    0.06
    sequential
    0.06
    (album
    0.06
    #=
    0.06
    toLocale
    0.06
     politique
    0.06
    VertexUvs
    0.06
    Act Density 0.018%

    No Known Activations