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

    Neuronpedia

    INDEX
    Explanations

    augmented reality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.49
    G
    0.48
    es
    0.47
    s
    0.43
    explorer
    0.42
    iz
    0.42
    planning
    0.41
    is
    0.40
    g
    0.40
    ir
    0.40
    POSITIVE LOGITS
    detailID
    0.49
    apadani
    0.44
     বিস্তারিত
    0.42
    ഒ
    0.42
    ചര്യ
    0.41
     абсолютно
    0.41
    ക്കെ
    0.40
     entirely
    0.40
     épais
    0.40
     بالکل
    0.40
    Act Density 0.003%

    No Known Activations