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

    Neuronpedia

    INDEX
    Explanations

    web security/domains

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ULONG
    -0.07
    ulur
    -0.06
    culate
    -0.06
    nodes
    -0.06
    ��
    -0.06
    _SETUP
    -0.06
    	Long
    -0.06
    string
    -0.06
    estate
    -0.06
     coop
    -0.06
    POSITIVE LOGITS
     teal
    0.07
     chiff
    0.07
     анти
    0.06
     Володими
    0.06
     beige
    0.06
     Em
    0.06
     cruis
    0.06
     push
    0.06
     üzerine
    0.06
     Lines
    0.06
    Act Density 0.173%

    No Known Activations