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

    Neuronpedia

    INDEX
    Explanations

    kwargs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Assess
    -0.07
     '.',
    -0.07
    	sm
    -0.07
     seaside
    -0.06
    spawn
    -0.06
     Stat
    -0.06
    Marker
    -0.06
     cartel
    -0.06
    .ReadInt
    -0.06
    Day
    -0.06
    POSITIVE LOGITS
    kwargs
    0.17
     kwargs
    0.11
    _kwargs
    0.10
    (kwargs
    0.08
     Kevin
    0.07
    _kw
    0.07
     revers
    0.07
     jButton
    0.07
     Jin
    0.07
     Advice
    0.06
    Act Density 0.001%

    No Known Activations