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

    Neuronpedia

    INDEX
    Explanations

    unwrap

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Destroy
    -0.08
     litter
    -0.06
    _bits
    -0.06
     VID
    -0.06
    _accel
    -0.06
     Migration
    -0.06
    Bel
    -0.06
    	memcpy
    -0.06
    paque
    -0.06
    LEX
    -0.06
    POSITIVE LOGITS
    unwrap
    0.08
    .unwrap
    0.07
     entrepreneurs
    0.07
    .weixin
    0.06
     Smash
    0.06
    -step
    0.06
    ใส
    0.06
    antro
    0.06
    मक
    0.06
     songwriter
    0.06
    Act Density 0.001%

    No Known Activations