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

    Neuronpedia

    INDEX
    Explanations

    in,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dělen
    -0.07
     unters
    -0.06
    จะ
    -0.06
     publishes
    -0.06
     geri
    -0.06
     Qualität
    -0.06
     dzie
    -0.06
    cats
    -0.06
    라이
    -0.06
    .authService
    -0.06
    POSITIVE LOGITS
    (MethodImplOptions
    0.07
     encrypt
    0.07
     Esper
    0.07
    [...,
    0.07
    arlo
    0.06
     intercept
    0.06
    ulg
    0.06
     genius
    0.06
    クション
    0.06
    _rg
    0.06
    Act Density 0.054%

    No Known Activations