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

    Neuronpedia

    INDEX
    Explanations

    selection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _EX
    -0.07
    )x
    -0.07
    up
    -0.07
    (style
    -0.07
     ])↵↵
    -0.07
     RAF
    -0.07
    γμα
    -0.07
     П
    -0.06
     talk
    -0.06
    灭
    -0.06
    POSITIVE LOGITS
     Selection
    0.07
     sele
    0.07
     toolkit
    0.07
    ()</
    0.06
    من
    0.06
     tém
    0.06
     selection
    0.06
    numeric
    0.06
    /~
    0.06
     Scarlet
    0.06
    Act Density 0.002%

    No Known Activations