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

    Neuronpedia

    INDEX
    Explanations

    Android error logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /\
    -0.07
    —"
    -0.07
    disconnect
    -0.07
     upt
    -0.07
    浓浓
    -0.06
    …”
    -0.06
     istediğ
    -0.06
    נוס
    -0.06
     שת
    -0.06
    bgcolor
    -0.06
    POSITIVE LOGITS
    Infrastructure
    0.07
    aim
    0.07
     kWh
    0.07
    acam
    0.07
    (IO
    0.07
     inher
    0.06
     curated
    0.06
     ads
    0.06
    chemas
    0.06
    有很大
    0.06
    Act Density 0.004%

    No Known Activations