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

    Neuronpedia

    INDEX
    Explanations

    explore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     menší
    -0.07
    {$
    -0.06
     suspected
    -0.06
    [#
    -0.06
    ILER
    -0.06
     says
    -0.06
     sizes
    -0.06
    ALCHEMY
    -0.06
    _MULT
    -0.06
     palp
    -0.06
    POSITIVE LOGITS
     explored
    0.12
     exploring
    0.09
     Explore
    0.08
     explore
    0.07
     roofing
    0.07
     nhận
    0.07
    Explore
    0.07
    .capitalize
    0.07
     computing
    0.07
    WR
    0.06
    Act Density 0.030%

    No Known Activations