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

    Neuronpedia

    INDEX
    Explanations

    Marketing/sales text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рик
    -0.07
    <Void
    -0.06
    .ent
    -0.06
    _qu
    -0.06
    vie
    -0.06
    ajor
    -0.06
    ident
    -0.06
    ancestor
    -0.06
    ####↵
    -0.06
     lol
    -0.06
    POSITIVE LOGITS
     socks
    0.06
     shalt
    0.06
     داش
    0.06
     deserialize
    0.06
    climate
    0.06
     commute
    0.06
     "->
    0.06
     Marines
    0.06
    MEA
    0.06
     ◄
    0.06
    Act Density 0.106%

    No Known Activations