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

    Neuronpedia

    INDEX
    Explanations

    ab

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ูม
    -0.07
     Graz
    -0.07
    Marc
    -0.07
     erotisk
    -0.07
     znám
    -0.06
    orent
    -0.06
     Jord
    -0.06
     Como
    -0.06
     Merk
    -0.06
    가요
    -0.06
    POSITIVE LOGITS
     Ab
    0.17
     ab
    0.17
    Ab
    0.14
     AB
    0.12
     Abraham
    0.12
    .ab
    0.11
     Abu
    0.10
    (ab
    0.10
     ABI
    0.10
     abi
    0.10
    Act Density 0.033%

    No Known Activations