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

    Neuronpedia

    INDEX
    Explanations

    studio

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    1.48
     on
    1.37
    2
    1.34
    مان
    1.15
    ig
    1.05
    ۲
    1.02
     is
    0.98
    ного
    0.92
    al
    0.91
    ed
    0.91
    POSITIVE LOGITS
    {
    1.13
     STUDIO
    1.12
    х
    1.12
     eléct
    1.08
     cambiamenti
    1.08
    き
    1.08
     суммы
    1.07
     fruto
    1.06
    {//
    1.05
     embarazada
    1.05
    Act Density 0.004%

    No Known Activations