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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tuned
    -0.06
     Př
    -0.06
    egend
    -0.06
     Toy
    -0.06
    uned
    -0.06
     interpret
    -0.06
     ------>
    -0.06
    �
    -0.06
    ents
    -0.06
     Крім
    -0.06
    POSITIVE LOGITS
    neck
    0.07
     wrapper
    0.06
    _TRIANGLE
    0.06
    čer
    0.06
     저장
    0.06
     січ
    0.06
    :@"
    0.06
     caf
    0.06
     HACK
    0.06
    sexo
    0.06
    Act Density 0.053%

    No Known Activations