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

    Neuronpedia

    INDEX
    Explanations

    describing features or content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     realignment
    0.39
    改
    0.39
     stör
    0.39
     angesch
    0.38
     rearrangements
    0.37
     halves
    0.37
    ئے
    0.36
     sprawy
    0.36
     policym
    0.36
    inally
    0.36
    POSITIVE LOGITS
    Description
    0.74
     Description
    0.73
    description
    0.71
     описание
    0.65
    Beschreibung
    0.64
     description
    0.61
     descripción
    0.59
     описа
    0.58
     डिस्क्रिप्शन
    0.57
    Descripción
    0.56
    Act Density 0.040%

    No Known Activations