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

    Neuronpedia

    INDEX
    Explanations

    answer to question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hibiscus
    0.76
     famílias
    0.76
     espect
    0.75
     yp
    0.74
    жин
    0.74
     PCP
    0.73
    стов
    0.71
    tDBOutput
    0.70
     liquide
    0.70
     disciplinas
    0.70
    POSITIVE LOGITS
     kepada
    1.14
     لهذا
    1.06
    แก่
    1.04
    への
    1.04
     thereto
    0.99
     لهذه
    0.94
    ដល់
    0.94
     terhadap
    0.93
     to
    0.87
     към
    0.86
    Act Density 0.122%

    No Known Activations