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

    Neuronpedia

    INDEX
    Explanations

    technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    age
    0.61
    ages
    0.60
    ouncements
    0.58
    ange
    0.56
    abus
    0.55
    argent
    0.55
    aging
    0.55
     nbsp
    0.55
     Engel
    0.55
    blog
    0.54
    POSITIVE LOGITS
    สำเร็จ
    0.58
     centena
    0.57
     हथ
    0.54
    悟
    0.54
    शांत
    0.53
     milhares
    0.52
    털
    0.51
    chim
    0.51
     sucesso
    0.50
    wir
    0.50
    Act Density 0.000%

    No Known Activations