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

    Neuronpedia

    INDEX
    Explanations

    love

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    έν
    -0.07
    quer
    -0.07
    NUMBER
    -0.07
     мер
    -0.07
    plr
    -0.07
    nowled
    -0.07
    micro
    -0.07
    inter
    -0.07
    like
    -0.07
     TERMIN
    -0.07
    POSITIVE LOGITS
     contextual
    0.06
     Ellen
    0.06
    �始化
    0.06
     decorative
    0.06
     straw
    0.06
     gebru
    0.06
    	wp
    0.06
     дотрим
    0.06
     Delaware
    0.06
    .jboss
    0.05
    Act Density 0.019%

    No Known Activations