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

    Neuronpedia

    INDEX
    Explanations

    comparisons in code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ToolStripButton
    -0.06
     department
    -0.06
    792
    -0.06
     Roku
    -0.06
    Injected
    -0.06
     lift
    -0.06
     lifts
    -0.06
     incoming
    -0.06
    elerden
    -0.06
    Rooms
    -0.06
    POSITIVE LOGITS
    ribly
    0.07
    采
    0.07
     Cel
    0.07
     Mega
    0.06
    ,const
    0.06
    /Observable
    0.06
     horrors
    0.06
    .functions
    0.06
    repid
    0.06
     hern
    0.06
    Act Density 0.009%

    No Known Activations