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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    libc
    -0.07
     duas
    -0.07
     Version
    -0.07
     visitors
    -0.06
     visiting
    -0.06
     Matthews
    -0.06
     Alphabet
    -0.06
     Barnes
    -0.06
     Ginger
    -0.06
     Martin
    -0.06
    POSITIVE LOGITS
    又
    0.06
     summons
    0.06
    ','','
    0.06
     suy
    0.06
     enlarg
    0.06
     віль
    0.06
    сам
    0.06
    (MenuItem
    0.06
    _FATAL
    0.06
     inflammatory
    0.06
    Act Density 0.133%

    No Known Activations