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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Charge
    -0.06
    _align
    -0.06
     alliance
    -0.06
     oracle
    -0.06
     플
    -0.06
    Component
    -0.06
    -functions
    -0.06
     channels
    -0.06
    INF
    -0.06
     Velocity
    -0.06
    POSITIVE LOGITS
    incorrect
    0.07
    unitOfWork
    0.07
    0.07
     checking
    0.07
     capacit
    0.06
    □□
    0.06
    ––
    0.06
    inidad
    0.06
     Planned
    0.06
    
    0.06
    Act Density 0.147%

    No Known Activations