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

    Neuronpedia

    INDEX
    Explanations

    content creation and argumentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    дачи
    0.45
    kis
    0.45
    ’
    0.41
    dür
    0.40
    Kis
    0.40
    s
    0.40
     Mpc
    0.40
    =="
    0.40
     Kis
    0.40
    "
    0.39
    POSITIVE LOGITS
    eful
    0.49
     Necklace
    0.47
     의견
    0.47
     opiniones
    0.46
     intravenously
    0.45
    aying
    0.44
    inuation
    0.44
    اعد
    0.44
     אור
    0.43
    𝓸
    0.43
    Act Density 0.000%

    No Known Activations