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

    Neuronpedia

    INDEX
    Explanations

    barbed wire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     accidents
    0.60
     बना
    0.60
     closures
    0.59
     infections
    0.56
     closets
    0.56
     않아
    0.55
     incidences
    0.55
    ties
    0.55
     isolating
    0.54
     चौ
    0.54
    POSITIVE LOGITS
     syg
    0.59
     úspě
    0.58
    x
    0.54
     Ababa
    0.53
     estrut
    0.52
    F
    0.52
    ISPW
    0.51
    例如
    0.51
     haber
    0.50
     svih
    0.50
    Act Density 0.000%

    No Known Activations