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

    Neuronpedia

    INDEX
    Explanations

    if conditions with parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    エラー
    0.44
    豪華
    0.43
    짬
    0.42
    Witam
    0.41
    Herkese
    0.40
    ᴿ
    0.40
    DOCTYPE
    0.39
     erro
    0.39
     boiler
    0.39
    erreur
    0.38
    POSITIVE LOGITS
    foreach
    0.46
     isset
    0.43
     [$
    0.43
    ares
    0.42
     foreach
    0.42
    assertInstanceOf
    0.42
    (($
    0.41
    [$
    0.40
    isset
    0.39
    (!$
    0.37
    Act Density 0.006%

    No Known Activations