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

    Neuronpedia

    INDEX
    Explanations

    Page numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     changed
    -0.07
     код
    -0.07
     nature
    -0.06
    飲
    -0.06
    減
    -0.06
    ByName
    -0.06
     이름
    -0.06
     led
    -0.06
     nonsense
    -0.06
    unga
    -0.06
    POSITIVE LOGITS
    �
    0.07
    からは
    0.06
    ailer
    0.06
    tor
    0.06
    _sys
    0.06
    sterol
    0.06
    Ep
    0.06
     prostit
    0.06
    igious
    0.06
    )init
    0.05
    Act Density 0.054%

    No Known Activations