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

    Neuronpedia

    INDEX
    Explanations

    unique

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _commands
    -0.07
    _distance
    -0.07
     meantime
    -0.06
    Bet
    -0.06
    Addresses
    -0.06
    .start
    -0.06
    .bit
    -0.06
    pectral
    -0.06
     curs
    -0.06
    騎
    -0.06
    POSITIVE LOGITS
    jourd
    0.07
    heiten
    0.07
     biệt
    0.07
    애
    0.07
     перс
    0.07
    ــــــــ
    0.07
     अलग
    0.07
     şek
    0.07
     unite
    0.07
    ΙΑΚ
    0.07
    Act Density 0.013%

    No Known Activations