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

    Neuronpedia

    INDEX
    Explanations

    screens, especially for displays or cameras

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    &
    0.62
    лось
    0.61
    1
    0.55
    +
    0.55
    ject
    0.52
    mid
    0.52
    เดียวกัน
    0.52
    vers
    0.50
    lim
    0.50
    (
    0.50
    POSITIVE LOGITS
     terutama
    0.86
     pecinta
    0.72
     movieId
    0.71
     tzv
    0.69
     tratamiento
    0.68
     tzw
    0.68
     especialmente
    0.68
     সিনেমা
    0.66
     radiotherapy
    0.65
     HUOBI
    0.65
    Act Density 0.004%

    No Known Activations