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

    Neuronpedia

    INDEX
    Explanations

    evolving or understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    acknowled
    0.41
     montagnes
    0.39
    MOTOR
    0.39
    gameObjects
    0.39
     montañas
    0.39
     पहाड़ों
    0.38
    MOUNTAINS
    0.38
    ्लादेश
    0.38
     विज्ञ
    0.38
     acknowledged
    0.37
    POSITIVE LOGITS
     thinning
    0.38
    òn
    0.38
    )(-
    0.36
    accar
    0.36
    다운
    0.35
     pac
    0.35
    idual
    0.34
     cell
    0.34
     paci
    0.34
     cast
    0.34
    Act Density 0.000%

    No Known Activations