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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    spinner
    -0.08
     DEST
    -0.07
    	de
    -0.07
    Ark
    -0.07
     terse
    -0.07
     fwd
    -0.07
    +r
    -0.07
    …↵
    -0.07
    :description
    -0.06
    抜
    -0.06
    POSITIVE LOGITS
    amentals
    0.07
     Ruby
    0.06
    _rule
    0.06
     tyre
    0.06
    ving
    0.06
    QUENCY
    0.06
     Mix
    0.06
     Tourism
    0.06
    viar
    0.06
    quila
    0.06
    Act Density 0.020%

    No Known Activations