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

    Neuronpedia

    INDEX
    Explanations

    Model deployment and serving

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     разум
    -0.08
    calc
    -0.08
     runs
    -0.08
     reasonably
    -0.08
     fundamento
    -0.08
     आरो
    -0.08
     kaupapa
    -0.08
     алх
    -0.08
    phyr
    -0.08
     لوب
    -0.08
    POSITIVE LOGITS
     serving
    0.18
     Serving
    0.17
    Serving
    0.16
     Served
    0.16
     served
    0.16
    serv
    0.16
    _serv
    0.15
     Serve
    0.15
    -serving
    0.15
     servir
    0.14
    Act Density 0.009%

    No Known Activations