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

    Neuronpedia

    INDEX
    Explanations

    combined, done, size, smooth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inicialmente
    0.45
     pä
    0.43
     españa
    0.41
     প্রথমে
    0.41
     initially
    0.41
     boiled
    0.40
     menjalani
    0.39
     Wszyst
    0.39
     cooked
    0.39
     enthalpies
    0.39
    POSITIVE LOGITS
    extra
    0.46
    even
    0.43
    ignore
    0.41
    ≈
    0.41
    悪
    0.41
    excluding
    0.40
    izeit
    0.40
    approx
    0.39
    urig
    0.39
    there
    0.39
    Act Density 0.034%

    No Known Activations