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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Percent
    -0.07
    222
    -0.07
    iled
    -0.06
    lland
    -0.06
    UNET
    -0.06
     ebooks
    -0.06
     withdrawing
    -0.06
    Ms
    -0.06
     Männer
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    _quotes
    0.07
     ifade
    0.06
     생활
    0.06
     державного
    0.06
     ainsi
    0.06
     unexpectedly
    0.06
     softmax
    0.06
    .statusCode
    0.06
    ETHOD
    0.06
    (Route
    0.06
    Act Density 0.068%

    No Known Activations