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

    Neuronpedia

    INDEX
    Explanations

    rights reserved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reserve
    0.53
     rights
    0.50
     reserves
    0.49
    reserve
    0.46
    Reserve
    0.46
     reserving
    0.45
    版权
    0.43
     Reserve
    0.43
     reserva
    0.43
     Rights
    0.42
    POSITIVE LOGITS
     construye
    0.46
    getTo
    0.44
     equilibrated
    0.42
     geométricas
    0.42
     postavlj
    0.42
    fillRect
    0.41
     instantiated
    0.41
    getToken
    0.40
    olska
    0.40
     razem
    0.40
    Act Density 0.000%

    No Known Activations