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

    Neuronpedia

    INDEX
    Explanations

    verify data accuracy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    trong
    0.40
    nehmer
    0.39
    তু
    0.38
    Mis
    0.37
    Particip
    0.37
     sensibilities
    0.37
    主人
    0.37
    Indian
    0.35
     especialista
    0.35
    Ped
    0.34
    POSITIVE LOGITS
    gesetz
    0.39
     Dale
    0.38
     escribir
    0.38
     Тен
    0.38
     manejar
    0.37
     hazard
    0.37
     dT
    0.37
     Cases
    0.37
     Cualquier
    0.37
     危
    0.37
    Act Density 0.000%

    No Known Activations