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

    Neuronpedia

    INDEX
    Explanations

    code snippets with keywords such as thread, lock, and new

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NUMX
    -0.84
     Chwiliwch
    -0.78
    $")
    -0.72
     Audiodateien
    -0.69
    `,
    -0.66
    styleUrls
    -0.66
     بيها
    -0.65
    ließlich
    -0.65
    StoreMessageInfo
    -0.63
    UnsafeEnabled
    -0.63
    POSITIVE LOGITS
     visibilité
    0.49
     aneurysm
    0.47
     stratégique
    0.45
     plagioclase
    0.45
     Levant
    0.44
     résine
    0.44
    hova
    0.43
    alsy
    0.43
    /**
    0.43
     livrer
    0.43
    Act Density 3.783%

    No Known Activations