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

    Neuronpedia

    INDEX
    Explanations

    Parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mathematical
    -0.07
    ательно
    -0.07
    namespace
    -0.07
    for
    -0.06
     dir
    -0.06
     demande
    -0.06
     Cleaning
    -0.06
     plutôt
    -0.06
    eu
    -0.06
    Rather
    -0.06
    POSITIVE LOGITS
    >".
    0.07
     çay
    0.06
     tinh
    0.06
    removeAttr
    0.06
     最
    0.06
    .SetFloat
    0.06
    ワイト
    0.06
     Personality
    0.06
    gency
    0.06
    .simps
    0.06
    Act Density 0.185%

    No Known Activations