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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tranquil
    -0.07
    /tag
    -0.06
    Gam
    -0.06
    ihar
    -0.06
    .custom
    -0.06
    _MARGIN
    -0.06
    astle
    -0.06
     зуп
    -0.06
    Mil
    -0.06
     Luke
    -0.06
    POSITIVE LOGITS
    positions
    0.07
    /MPL
    0.07
    ξε
    0.06
     Ende
    0.06
    nelle
    0.06
    Represent
    0.06
    하
    0.06
     utilizing
    0.06
    .scrollView
    0.06
    landı
    0.06
    Act Density 0.000%

    No Known Activations