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

    Neuronpedia

    INDEX
    Explanations

    Benedict

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Schumer
    -0.07
     무
    -0.07
    .startDate
    -0.06
    Psi
    -0.06
     lorem
    -0.06
    (rng
    -0.06
    lower
    -0.06
    Double
    -0.06
     Psi
    -0.06
    loom
    -0.06
    POSITIVE LOGITS
     PdfPCell
    0.07
    攻撃
    0.07
     gelenek
    0.06
     compliments
    0.06
    .define
    0.06
     punish
    0.06
    之
    0.06
    pun
    0.06
     Bringing
    0.06
     görüntü
    0.06
    Act Density 0.002%

    No Known Activations