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

    Neuronpedia

    INDEX
    Explanations

    a hidden

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    z
    0.54
    zach
    0.47
    atron
    0.44
    kých
    0.42
    արգ
    0.41
     గారి
    0.41
    했으며
    0.41
    zul
    0.40
    <0xBB>
    0.40
    arik
    0.39
    POSITIVE LOGITS
    resident
    0.49
     jugando
    0.49
     alue
    0.49
     đa
    0.48
     ous
    0.48
     jugador
    0.47
     бассе
    0.47
     coeficiente
    0.47
    رسٹ
    0.47
     colesterol
    0.47
    Act Density 0.000%

    No Known Activations