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

    Neuronpedia

    INDEX
    Explanations

    math game theory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     toque
    -0.08
     credited
    -0.08
     gentle
    -0.08
     dedicada
    -0.08
     qul
    -0.08
     herz
    -0.08
    credit
    -0.08
     dedicado
    -0.07
     offic
    -0.07
     rustic
    -0.07
    POSITIVE LOGITS
     выбран
    0.09
     deciding
    0.09
     uncontrolled
    0.09
     nightmare
    0.08
    Chosen
    0.08
     cheaply
    0.08
     заранее
    0.08
     foreseeable
    0.08
    _selected
    0.08
     unpredict
    0.08
    Act Density 0.026%

    No Known Activations