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

    Neuronpedia

    INDEX
    Explanations

    logical arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    іно
    -0.06
     started
    -0.06
     varchar
    -0.06
    ToWorld
    -0.06
     Wheeler
    -0.06
     utterly
    -0.06
    ERSIST
    -0.06
    ONENT
    -0.06
    [F
    -0.06
    Started
    -0.06
    POSITIVE LOGITS
     thaimassage
    0.07
     Compliance
    0.07
     Ply
    0.07
     sah
    0.06
    ัดส
    0.06
    /#
    0.06
     tam
    0.06
     blí
    0.06
     hacked
    0.06
    ılmaz
    0.06
    Act Density 0.010%

    No Known Activations