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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rire
    -0.07
     Starting
    -0.07
     render
    -0.06
     процессе
    -0.06
    "When
    -0.06
     asserted
    -0.06
    ）。
    -0.06
    .Cells
    -0.06
     나라
    -0.06
    MK
    -0.06
    POSITIVE LOGITS
    -big
    0.07
     Велик
    0.06
    �
    0.06
     eser
    0.06
     ван
    0.06
     altı
    0.06
     orbs
    0.06
    集中
    0.06
     slou
    0.06
     payday
    0.06
    Act Density 0.010%

    No Known Activations