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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     asserts
    -0.06
     influences
    -0.06
     Chang
    -0.06
     sama
    -0.06
    ırak
    -0.06
    erequisite
    -0.06
     ponto
    -0.06
     blend
    -0.06
     scared
    -0.06
     Eval
    -0.06
    POSITIVE LOGITS
     Stroke
    0.07
    902
    0.07
    Regions
    0.06
    键
    0.06
    lobals
    0.06
    олов
    0.06
     socialist
    0.06
     Gregg
    0.06
    146
    0.06
     chancellor
    0.06
    Act Density 0.005%

    No Known Activations