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

    Neuronpedia

    INDEX
    Explanations

    Rust code keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    淍
    0.50
    чью
    0.45
     Fabrizio
    0.42
     Anu
    0.41
     dimanche
    0.40
    恸
    0.40
     जींस
    0.40
    ।]
    0.40
    ڎ
    0.39
     EDTA
    0.39
    POSITIVE LOGITS
    let
    1.05
    match
    1.00
     match
    0.90
     let
    0.89
    if
    0.75
    println
    0.74
    unsafe
    0.63
    assert
    0.63
     Match
    0.62
     Let
    0.59
    Act Density 0.021%

    No Known Activations