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
     kasarigan
    -0.61
    contentLoaded
    -0.60
    transQ
    -0.57
     actionMode
    -0.56
    󠁴
    -0.55
    okovic
    -0.54
     tartalomajánló
    -0.51
     préfère
    -0.48
    vrigt
    -0.48
     uchiha
    -0.48
    POSITIVE LOGITS
     its
    0.71
    </thead>
    0.71
    GEBURTSDATUM
    0.66
    BoxShadow
    0.64
     the
    0.63
    bootstrapcdn
    0.59
    sstream
    0.58
     new
    0.57
    PYX
    0.55
    quilla
    0.55
    Act Density 0.001%

    No Known Activations