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

    Neuronpedia

    INDEX
    Explanations

    said

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    opia
    -0.07
     london
    -0.07
    OPER
    -0.07
    QPushButton
    -0.07
    annotation
    -0.06
    ？↵
    -0.06
    ?>
    -0.06
    .UP
    -0.06
    _shuffle
    -0.06
    /include
    -0.06
    POSITIVE LOGITS
     says
    0.07
    번째
    0.06
    ilinear
    0.06
     используют
    0.06
     combines
    0.06
    (channel
    0.06
     kaz
    0.06
    plementation
    0.06
    (ds
    0.06
     letras
    0.06
    Act Density 0.017%

    No Known Activations