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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lamaz
    -0.06
    .locale
    -0.06
     convincing
    -0.06
     proteins
    -0.06
    .setScale
    -0.06
    RefCount
    -0.06
    น
    -0.06
    IH
    -0.06
    اوية
    -0.06
    .jp
    -0.06
    POSITIVE LOGITS
    141
    0.07
    tie
    0.07
    +lsi
    0.07
     จาก
    0.07
     pk
    0.07
     خوبی
    0.07
     Nazi
    0.06
    _travel
    0.06
     usa
    0.06
    (st
    0.06
    Act Density 0.030%

    No Known Activations