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

    Neuronpedia

    INDEX
    Explanations

    conversational writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    َو
    -0.07
    mob
    -0.07
    raham
    -0.07
     dear
    -0.06
    kh
    -0.06
     eyes
    -0.06
    wig
    -0.06
    columnName
    -0.06
     decad
    -0.06
     Utilities
    -0.06
    POSITIVE LOGITS
     mongoose
    0.07
    人気
    0.06
     UIGraphics
    0.06
     требуется
    0.06
    .rx
    0.06
    DivElement
    0.06
    Autoresizing
    0.06
    Spr
    0.06
    .number
    0.06
     жив
    0.06
    Act Density 0.117%

    No Known Activations