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

    Neuronpedia

    INDEX
    Explanations

    require

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     played
    -0.07
     stolen
    -0.07
     haut
    -0.07
     girl
    -0.06
     cool
    -0.06
    �
    -0.06
     cavern
    -0.06
     walks
    -0.06
     seen
    -0.06
     went
    -0.06
    POSITIVE LOGITS
     requires
    0.11
     require
    0.10
     required
    0.09
     requiring
    0.09
     Requires
    0.08
    .requires
    0.08
     předpok
    0.08
    RESH
    0.07
     Require
    0.07
    (require
    0.07
    Act Density 0.054%

    No Known Activations