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

    Neuronpedia

    INDEX
    Explanations

    Measurement and quantity concepts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .bukkit
    -0.07
    _Destroy
    -0.07
     Bukkit
    -0.07
     Cincinnati
    -0.07
     strapped
    -0.07
     cake
    -0.07
    _READ
    -0.06
    belt
    -0.06
     Byrne
    -0.06
    روف
    -0.06
    POSITIVE LOGITS
     Mumbai
    0.07
     Pune
    0.06
    Producer
    0.06
     Pricing
    0.06
    igrations
    0.06
     Gujar
    0.06
    weeks
    0.06
     examines
    0.05
     receber
    0.05
     Optionally
    0.05
    Act Density 0.089%

    No Known Activations