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

    Neuronpedia

    INDEX
    Explanations

    porn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    show
    -0.07
    Show
    -0.07
    -cell
    -0.06
    .degree
    -0.06
    ด
    -0.06
    Extractor
    -0.06
     legalized
    -0.06
    ột
    -0.06
    ends
    -0.06
    몬
    -0.06
    POSITIVE LOGITS
    ipherals
    0.08
     Barrel
    0.07
     dev
    0.07
    _vlan
    0.07
    /')
    0.07
     np
    0.07
    	dst
    0.06
     numpy
    0.06
     clinics
    0.06
     путем
    0.06
    Act Density 0.036%

    No Known Activations