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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    such
    -0.07
     bella
    -0.07
     therein
    -0.07
    default
    -0.07
     thanks
    -0.07
    _BOOK
    -0.07
     status
    -0.07
    <{
    -0.06
     boring
    -0.06
     Bet
    -0.06
    POSITIVE LOGITS
    Layers
    0.07
    QR
    0.06
    textInput
    0.06
    ,and
    0.06
    �n
    0.06
    _DER
    0.06
    führ
    0.06
     Candidates
    0.06
    _PWM
    0.06
     Wid
    0.06
    Act Density 0.198%

    No Known Activations