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

    Neuronpedia

    INDEX
    Explanations

    Score

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     libertarian
    -0.09
     Sullivan
    -0.08
    ":-
    -0.08
     Speedway
    -0.08
     Hamilton
    -0.08
     variables
    -0.07
    威廉
    -0.07
     variable
    -0.07
     kingdom
    -0.07
    unità
    -0.07
    POSITIVE LOGITS
    ười
    0.08
    _score
    0.08
     scored
    0.08
     Score
    0.07
    スター
    0.07
    .shader
    0.07
    0.07
    得太
    0.07
    -os
    0.07
    abet
    0.07
    Act Density 0.024%

    No Known Activations