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

    Neuronpedia

    INDEX
    Explanations

    loops

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     physicians
    -0.08
     physician
    -0.07
    _stats
    -0.07
     för
    -0.07
     dysfunctional
    -0.07
    rell
    -0.06
    coach
    -0.06
    edik
    -0.06
     rak
    -0.06
    }},
    -0.06
    POSITIVE LOGITS
    (World
    0.06
     ofstream
    0.06
    .ModelSerializer
    0.06
     एम
    0.06
     اب
    0.06
    Probability
    0.06
     داستان
    0.06
    enty
    0.06
    .createParallelGroup
    0.06
    recision
    0.06
    Act Density 0.146%

    No Known Activations