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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recip
    -0.06
    퍼
    -0.06
     riot
    -0.06
     greatest
    -0.06
     upcoming
    -0.06
     anew
    -0.06
     beverages
    -0.06
    ű
    -0.06
    _lead
    -0.06
     paraph
    -0.06
    POSITIVE LOGITS
    Ÿ
    0.08
     Mädchen
    0.08
     Return
    0.07
    ductor
    0.06
    .VERTICAL
    0.06
    ancia
    0.06
    .Fecha
    0.06
     Slam
    0.06
    шибка
    0.06
    .follow
    0.06
    Act Density 0.068%

    No Known Activations