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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    通信
    -0.06
     Rog
    -0.06
    _stand
    -0.06
    _nv
    -0.06
     mensagem
    -0.06
     этого
    -0.06
     ис
    -0.06
     ;↵↵↵
    -0.06
    -Language
    -0.06
    967
    -0.05
    POSITIVE LOGITS
     Dental
    0.07
    .drawer
    0.07
     cautious
    0.06
     Rick
    0.06
     Monitor
    0.06
     Pharma
    0.06
    Rick
    0.06
     Mississippi
    0.06
    (plot
    0.06
    ्ट
    0.06
    Act Density 0.002%

    No Known Activations