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

    Neuronpedia

    INDEX
    Explanations

    the word "permanent" and Japanese ideograms/punctuation

    oai_token-act-pair · gemini-2.0-flash

    Japanese and Java

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ly
    -0.66
    theless
    -0.64
    )");
    -0.60
    BufferException
    -0.60
    .";
    -0.59
    いらっしゃ
    -0.56
    :");
    -0.55
    المناصب
    -0.54
    Personendaten
    -0.54
     незавершена
    -0.53
    POSITIVE LOGITS
     useContext
    0.67
    zeuge
    0.67
    frig
    0.66
    ChildIndex
    0.65
    ße
    0.63
    +#+
    0.63
    setContentView
    0.63
    ropoda
    0.62
    brev
    0.59
    estruct
    0.59
    Act Density 0.097%

    No Known Activations