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

    Neuronpedia

    INDEX
    Explanations

    tricks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LC
    -0.06
     awful
    -0.06
     tenants
    -0.06
    Few
    -0.06
    ौन
    -0.06
     hurried
    -0.06
    PE
    -0.06
    (prompt
    -0.06
    def
    -0.06
     plasma
    -0.06
    POSITIVE LOGITS
     tricks
    0.14
     Tricks
    0.11
     соверш
    0.07
     Worlds
    0.07
    stral
    0.07
     등을
    0.06
     ForCanBeConvertedToForeach
    0.06
    ▍▍
    0.06
     QRect
    0.06
    Review
    0.06
    Act Density 0.005%

    No Known Activations