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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     folders
    -0.07
     lords
    -0.06
     servers
    -0.06
    ثير
    -0.06
     steadily
    -0.06
     folder
    -0.06
     economies
    -0.06
    (files
    -0.06
     onwards
    -0.06
    their
    -0.06
    POSITIVE LOGITS
    الك
    0.07
     صنعت
    0.07
    Td
    0.07
    ζει
    0.07
    _WAKE
    0.06
     Fortnite
    0.06
    alternate
    0.06
    opause
    0.06
    Robot
    0.06
    PUR
    0.06
    Act Density 0.026%

    No Known Activations