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

    Neuronpedia

    INDEX
    Explanations

    _handler

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     standardized
    -0.10
    _pic
    -0.09
     guy
    -0.08
     ekip
    -0.08
     pep
    -0.08
    -0.08
     presentation
    -0.08
    Presentation
    -0.07
     बेट
    -0.07
     iceberg
    -0.07
    POSITIVE LOGITS
    (/^
    0.10
     Expertise
    0.09
     spezialisiert
    0.09
     /\.
    0.08
     Trigger
    0.08
     experts
    0.08
     uzman
    0.08
     эксперт
    0.08
     gjelder
    0.08
     décl
    0.07
    Act Density 0.001%
    No Known Activations