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

    Neuronpedia

    INDEX
    Explanations

    permissions/laws

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     técnica
    -0.08
    Displaying
    -0.07
     litr
    -0.07
    Disposed
    -0.07
    iosity
    -0.07
    hardware
    -0.07
     vaj
    -0.07
     Malt
    -0.07
     comfortably
    -0.07
    Busy
    -0.07
    POSITIVE LOGITS
     предусматри
    0.12
     looph
    0.12
     künftig
    0.11
     banning
    0.10
     overhaul
    0.10
    禁止
    0.10
     provisions
    0.10
     exemptions
    0.10
     federal
    0.10
     protections
    0.09
    Act Density 0.185%

    No Known Activations