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

    Neuronpedia

    INDEX
    Explanations

    body parts inflammation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cuộc
    -0.07
    	driver
    -0.07
    óng
    -0.07
     suc
    -0.07
     בעלי
    -0.07
     antim
    -0.07
    ực
    -0.07
     Christianity
    -0.07
     lifecycle
    -0.07
    iller
    -0.06
    POSITIVE LOGITS
    🤫
    0.08
    _sound
    0.08
    (Position
    0.07
    (^
    0.07
    ActivityResult
    0.07
    IRR
    0.07
    eware
    0.06
    comments
    0.06
    (Function
    0.06
    Violation
    0.06
    Act Density 0.022%

    No Known Activations