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

    Neuronpedia

    INDEX
    Explanations

    false or misleading content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.39
    Rivers
    0.39
    Aggregation
    0.33
    হ
    0.32
     Rivers
    0.32
     Rios
    0.31
    Q
    0.31
     $\
    0.31
    K
    0.31
    $\
    0.30
    POSITIVE LOGITS
    ных
    0.34
    relle
    0.30
     অবগত
    0.30
    ной
    0.29
    ла
    0.29
    atically
    0.29
    carrito
    0.29
    вых
    0.29
     eigenlijk
    0.29
     городского
    0.29
    Act Density 0.013%

    No Known Activations