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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ')}}↵
    -0.06
     faz
    -0.06
    axter
    -0.06
     lookout
    -0.06
     грн
    -0.06
    uits
    -0.06
    ابی
    -0.06
    فصل
    -0.06
    玉
    -0.06
     freshwater
    -0.06
    POSITIVE LOGITS
    -----↵
    0.07
    ...,
    0.06
    .Qt
    0.06
     숙
    0.06
     Thời
    0.06
     DET
    0.06
    ضي
    0.06
    …the
    0.06
    Besides
    0.06
    +='
    0.06
    Act Density 0.008%

    No Known Activations