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

    Neuronpedia

    INDEX
    Explanations

    do

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ingredient
    -0.07
    Ин
    -0.07
     Slo
    -0.06
     Mama
    -0.06
     λ
    -0.06
     Μαρ
    -0.06
    ีอ
    -0.06
     savings
    -0.06
    theory
    -0.06
    ưởng
    -0.06
    POSITIVE LOGITS
     large
    0.07
    wald
    0.06
    ('');↵
    0.06
    :UIControl
    0.06
    NullOr
    0.06
    αλύτε
    0.06
    Looper
    0.06
     Vog
    0.06
    �
    0.06
    RenderingContext
    0.06
    Act Density 0.020%

    No Known Activations