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

    Neuronpedia

    INDEX
    Explanations

    schedules and events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    акон
    -0.07
     MIS
    -0.07
    BSD
    -0.06
    dirs
    -0.06
     yararlan
    -0.06
    (Status
    -0.06
     Cree
    -0.06
    SWEP
    -0.06
    urse
    -0.06
     Rather
    -0.06
    POSITIVE LOGITS
     heyec
    0.07
    +'_
    0.07
    onte
    0.06
     ln
    0.06
     ':
    0.06
     thật
    0.06
     insanely
    0.06
    Andrew
    0.06
    啪
    0.06
    Genesis
    0.06
    Act Density 0.057%

    No Known Activations