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

    Neuronpedia

    INDEX
    Explanations

    genes and elements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     perfume
    -0.07
    WRITE
    -0.07
    Writer
    -0.07
    versed
    -0.07
    Ke
    -0.07
    畫
    -0.06
    ugen
    -0.06
    ticket
    -0.06
     важно
    -0.06
    -available
    -0.06
    POSITIVE LOGITS
     داستان
    0.07
     sklearn
    0.06
     темп
    0.06
     Му
    0.06
     takové
    0.06
    ิป
    0.06
     oats
    0.06
     Cent
    0.06
     steal
    0.06
    _mE
    0.06
    Act Density 0.036%

    No Known Activations