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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NotImplementedError
    -0.07
    60
    -0.06
    _allocation
    -0.06
     become
    -0.06
    .done
    -0.06
    _NOTIFICATION
    -0.06
    lsru
    -0.06
     наві
    -0.06
    $values
    -0.06
    (actual
    -0.06
    POSITIVE LOGITS
    rsa
    0.07
     adjusting
    0.07
     scars
    0.07
     strategy
    0.07
    iker
    0.06
     spelled
    0.06
     resized
    0.06
    OTA
    0.06
    教
    0.06
     dressed
    0.06
    Act Density 0.000%

    No Known Activations