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

    Neuronpedia

    INDEX
    Explanations

    (result

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     начина
    -0.07
    یین
    -0.07
     iniciar
    -0.06
    ेबस
    -0.06
    ấm
    -0.06
    。（
    -0.06
    welcome
    -0.06
    Io
    -0.06
    semb
    -0.06
     สำน
    -0.06
    POSITIVE LOGITS
    .cleaned
    0.07
    _SEGMENT
    0.07
    ,:]
    0.06
    스
    0.06
    df
    0.06
    _truth
    0.06
     ItemStack
    0.06
    .POS
    0.06
    \/
    0.06
     swamp
    0.06
    Act Density 0.025%

    No Known Activations