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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     takdir
    -0.07
     пас
    -0.07
     законодатель
    -0.06
     insistence
    -0.06
    -follow
    -0.06
    .Players
    -0.06
    eax
    -0.06
     barrage
    -0.06
    @qq
    -0.06
     Esto
    -0.06
    POSITIVE LOGITS
     мужчин
    0.07
    minus
    0.07
     =>{↵
    0.07
    RIX
    0.07
     ()=>{↵
    0.07
    {↵
    0.07
    =>{↵
    0.06
     adc
    0.06
    ΙΛ
    0.06
     человечес
    0.06
    Act Density 0.016%

    No Known Activations