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

    Neuronpedia

    INDEX
    Explanations

    nombre, valor, numero

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    1.05
    ای
    1.00
    یت
    0.96
    나
    0.96
    یل
    0.93
    “
    0.91
     soaring
    0.91
    א
    0.88
    고
    0.88
    P
    0.85
    POSITIVE LOGITS
     Etiquetas
    1.00
    ta
    0.91
    𝟐
    0.87
    <unused643>
    0.85
     Usuario
    0.84
    ()){
    0.83
    ang
    0.82
    ם
    0.82
     دليل
    0.82
    2
    0.81
    Act Density 0.030%

    No Known Activations