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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     whenever
    -0.07
     However
    -0.06
     which
    -0.06
     apocalypse
    -0.06
     peanuts
    -0.06
     simplicity
    -0.06
     validated
    -0.06
    ربع
    -0.06
     '{@
    -0.06
     Particularly
    -0.06
    POSITIVE LOGITS
    ピ
    0.07
    dialogs
    0.07
    Edward
    0.07
    duto
    0.06
    lán
    0.06
    apeake
    0.06
    вищ
    0.06
    َّ
    0.06
    �
    0.06
    ische
    0.06
    Act Density 0.362%

    No Known Activations