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

    Neuronpedia

    INDEX
    Explanations

    codepen code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (SE
    -0.06
    anta
    -0.06
    ,number
    -0.06
    _idxs
    -0.06
    Ｃ
    -0.06
    Enviar
    -0.06
    　　　　　　　　　　　　　
    -0.06
    printw
    -0.06
     Ming
    -0.06
    Tau
    -0.06
    POSITIVE LOGITS
     hello
    0.07
     hp
    0.07
     урож
    0.06
    训
    0.06
    illance
    0.06
    Public
    0.06
    호
    0.06
    ">'.
    0.06
    avenous
    0.06
    Remaining
    0.06
    Act Density 0.002%

    No Known Activations