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

    Neuronpedia

    INDEX
    Explanations

    say number 1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rh
    -0.07
     Лю
    -0.07
     jednak
    -0.07
    這是
    -0.06
    ⓛ
    -0.06
    nger
    -0.06
     fram
    -0.06
    Quant
    -0.06
     بر
    -0.06
     pequ
    -0.06
    POSITIVE LOGITS
     centers
    0.08
    <input
    0.07
    _ALIGNMENT
    0.07
     escorte
    0.07
     frowned
    0.07
     Worst
    0.07
     NOP
    0.07
     '<
    0.07
    _no
    0.07
     ordinances
    0.07
    Act Density 0.002%

    No Known Activations