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

    Neuronpedia

    INDEX
    Explanations

    reporting numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     volonté
    0.38
     habis
    0.37
     foolproof
    0.37
     opposites
    0.35
     lika
    0.35
     hết
    0.35
     více
    0.35
     berpikir
    0.34
     여러
    0.34
     Einige
    0.34
    POSITIVE LOGITS
    7
    0.34
    B
    0.34
    R
    0.34
    I
    0.33
    H
    0.33
    Feb
    0.33
    X
    0.32
    was
    0.32
    A
    0.32
    M
    0.32
    Act Density 0.018%

    No Known Activations