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

    Neuronpedia

    INDEX
    Explanations

    diverse languages and topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    F
    0.61
    BRE
    0.52
    S
    0.51
    IN
    0.49
    AN
    0.47
    AS
    0.47
    PRO
    0.47
    MON
    0.47
    Jed
    0.47
     PRO
    0.46
    POSITIVE LOGITS
     există
    0.49
    カジュアル
    0.48
     pakai
    0.47
     decorative
    0.47
     compradores
    0.47
     kullanılır
    0.46
     मार्केट
    0.46
     chicas
    0.46
     productos
    0.45
     amerikan
    0.45
    Act Density 0.008%

    No Known Activations