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

    Neuronpedia

    INDEX
    Explanations

    Research, IRB

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	bl
    -0.07
     ML
    -0.07
    Provides
    -0.07
     SGD
    -0.06
     FileAccess
    -0.06
    .zip
    -0.06
     favors
    -0.06
    不斷
    -0.06
    _Call
    -0.06
     Confirmation
    -0.06
    POSITIVE LOGITS
     STEM
    0.07
     Remaining
    0.06
     Erica
    0.06
    paid
    0.06
    ender
    0.06
     servo
    0.06
    _len
    0.06
     limit
    0.06
     analyzer
    0.06
    	world
    0.06
    Act Density 0.002%

    No Known Activations