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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (UINT
    -0.06
     apar
    -0.06
    EventHandler
    -0.06
    clipse
    -0.06
     hãng
    -0.06
     bisa
    -0.06
     acheter
    -0.06
    interp
    -0.06
     useClass
    -0.06
    üb
    -0.06
    POSITIVE LOGITS
    /math
    0.07
    0.06
    だけ
    0.06
    ────────
    0.06
    Wik
    0.06
    :The
    0.06
    903
    0.06
    .IsSuccess
    0.06
    бы
    0.06
     Deutschland
    0.06
    Act Density 0.024%

    No Known Activations