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

    Neuronpedia

    INDEX
    Explanations

    collections of objects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nós
    -0.08
    -ag
    -0.08
    �
    -0.08
    rades
    -0.07
     этих
    -0.07
    -base
    -0.07
     этой
    -0.07
    _identity
    -0.07
    Agent
    -0.07
    穗
    -0.07
    POSITIVE LOGITS
     rehab
    0.07
     kidnapping
    0.07
     overhaul
    0.06
    .DOWN
    0.06
    .Results
    0.06
    anyahu
    0.06
     ObjectId
    0.06
     Rolled
    0.06
     Hardcover
    0.06
    constitutional
    0.06
    Act Density 0.128%

    No Known Activations