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

    Neuronpedia

    INDEX
    Explanations

    article/

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    And
    0.30
    Perform
    0.30
    Plan
    0.28
     Natürlich
    0.27
    Tail
    0.27
    Solver
    0.27
    Below
    0.27
     použití
    0.26
    Tube
    0.26
    اور
    0.26
    POSITIVE LOGITS
    article
    0.53
     article
    0.50
     articulo
    0.46
     detal
    0.43
     artigo
    0.41
    6
    0.40
    7
    0.39
     detalle
    0.38
    9
    0.38
     articles
    0.37
    Act Density 0.024%

    No Known Activations