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

    Neuronpedia

    INDEX
    Explanations

    research results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     svn
    -0.07
     Osama
    -0.06
    aml
    -0.06
     Angebot
    -0.06
    ControlItem
    -0.06
     Sri
    -0.06
     contagious
    -0.06
    (factor
    -0.06
    -(
    -0.06
    Officers
    -0.06
    POSITIVE LOGITS
    umbles
    0.07
     長
    0.06
     OTHERWISE
    0.06
    νι
    0.06
    оні
    0.06
     apiUrl
    0.06
     Venue
    0.06
     #@
    0.06
    .positions
    0.06
    anuts
    0.06
    Act Density 0.022%

    No Known Activations