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

    Neuronpedia

    INDEX
    Explanations

    PP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ivalent
    -0.07
    apas
    -0.07
     باید
    -0.06
    13
    -0.06
    iydi
    -0.06
    отя
    -0.06
     damned
    -0.06
    ！↵↵↵↵
    -0.06
    gan
    -0.06
    жд
    -0.06
    POSITIVE LOGITS
     Sunny
    0.19
     Brisbane
    0.17
     preamble
    0.14
    unny
    0.11
    reamble
    0.09
    .opensource
    0.09
    abcdef
    0.09
    .Mockito
    0.09
     passphrase
    0.08
     Benghazi
    0.08
    Act Density 0.002%

    No Known Activations