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

    Neuronpedia

    INDEX
    Explanations

    LastName existence commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    久的
    0.45
    V
    0.42
     Seni
    0.41
     lord
    0.41
    cken
    0.41
    uco
    0.40
     chimique
    0.40
     সংসারে
    0.40
     reino
    0.39
    freien
    0.39
    POSITIVE LOGITS
    ⎮
    0.48
     abnormalities
    0.46
    চনায়
    0.46
    *_
    0.45
     unwarranted
    0.45
     Protecting
    0.45
     incompatibility
    0.45
     interpretations
    0.44
     unanswered
    0.44
    failures
    0.44
    Act Density 0.002%

    No Known Activations