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

    Neuronpedia

    INDEX
    Explanations

    Attribution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Related
    -0.07
    unidad
    -0.07
    �
    -0.07
     mesaj
    -0.07
    олет
    -0.06
    Intent
    -0.06
    -related
    -0.06
    stras
    -0.06
    itos
    -0.06
     chest
    -0.06
    POSITIVE LOGITS
     skyrocket
    0.06
     Automation
    0.06
     rates
    0.06
    uyu
    0.06
    Veter
    0.06
     může
    0.06
     ธ
    0.06
     средство
    0.06
    NETWORK
    0.06
     gre
    0.06
    Act Density 0.001%

    No Known Activations