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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ##↵
    -0.06
     المس
    -0.06
    bra
    -0.06
     sagt
    -0.06
    /git
    -0.06
     dansk
    -0.06
    .includes
    -0.06
    อเม
    -0.06
     relies
    -0.06
    exampleInputEmail
    -0.06
    POSITIVE LOGITS
     be
    0.08
     &[
    0.07
    oodle
    0.07
    钢
    0.06
    巴
    0.06
     YYSTACK
    0.06
    UserID
    0.06
    乳
    0.06
    Playable
    0.06
    setDefault
    0.06
    Act Density 0.046%

    No Known Activations