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

    Neuronpedia

    INDEX
    Explanations

    merging lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     שינוי
    -0.08
     change
    -0.07
    ιά
    -0.07
     phishing
    -0.07
    Change
    -0.07
    etragen
    -0.07
     બદલ
    -0.07
    áp
    -0.07
     बदल
    -0.07
     workplaces
    -0.07
    POSITIVE LOGITS
    贡
    0.10
    Merged
    0.09
     weaving
    0.09
     aficionados
    0.09
     bò
    0.08
    Meanwhile
    0.08
    _priority
    0.08
    comparison
    0.08
     merged
    0.08
    (priority
    0.08
    Act Density 0.008%

    No Known Activations