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

    Neuronpedia

    INDEX
    Explanations

    EN

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kadar
    -0.07
     Αγγ
    -0.07
     Hoàng
    -0.06
    .ONE
    -0.06
     zim
    -0.06
     MUST
    -0.06
     Users
    -0.06
    sciously
    -0.06
     크
    -0.06
     TMP
    -0.06
    POSITIVE LOGITS
    Catch
    0.07
    dění
    0.07
    眉
    0.06
    mey
    0.06
    aes
    0.06
     مصر
    0.06
    .published
    0.06
     muster
    0.06
    орг
    0.06
    lator
    0.06
    Act Density 0.002%

    No Known Activations