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

    Neuronpedia

    INDEX
    Explanations

    assignments and variable assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     funcionan
    0.47
     göstere
    0.46
     considéré
    0.45
    மாகவும்
    0.44
    ദ്ധ
    0.44
     afectan
    0.44
     considère
    0.44
     मार्गदर्शन
    0.43
    ⤟
    0.43
     வழிபட்ட
    0.42
    POSITIVE LOGITS
     =
    1.20
     :=
    0.77
    _
    0.68
     <-
    0.63
    =
    0.63
     =(
    0.61
    =(
    0.60
        
    0.60
    =((
    0.59
     is
    0.58
    Act Density 0.108%

    No Known Activations