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

    Neuronpedia

    INDEX
    Explanations

    literary review and analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    en
    0.41
    rera
    0.41
     RIA
    0.40
    est
    0.39
    on
    0.39
    lfloor
    0.39
    坚定
    0.39
    me
    0.39
    radius
    0.39
    ég
    0.38
    POSITIVE LOGITS
     литератур
    0.59
     Figuren
    0.56
    Liter
    0.54
     liter
    0.52
     Literal
    0.50
     Literary
    0.50
     Liter
    0.49
     ادبی
    0.49
     Literatura
    0.48
     литера
    0.46
    Act Density 0.006%

    No Known Activations