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

    Neuronpedia

    INDEX
    Explanations

    common

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .variant
    -0.07
     Burr
    -0.07
    まで
    -0.07
    .fin
    -0.07
    เกาะ
    -0.06
     Kushner
    -0.06
    (Calendar
    -0.06
     玩
    -0.06
     Sevent
    -0.06
    restrict
    -0.06
    POSITIVE LOGITS
    we
    0.06
    -carousel
    0.06
    rend
    0.06
    ilen
    0.06
     Utt
    0.06
    verity
    0.06
    :Is
    0.06
    ربی
    0.06
    posta
    0.06
    shall
    0.06
    Act Density 0.029%

    No Known Activations