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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    endTime
    -0.08
     Wag
    -0.07
     المه
    -0.06
    efore
    -0.06
    ocoder
    -0.06
    _lex
    -0.06
    .arc
    -0.06
    ENC
    -0.06
    pid
    -0.06
     carcin
    -0.06
    POSITIVE LOGITS
     gute
    0.07
    (updated
    0.06
     treffen
    0.06
     Thumbnail
    0.06
     OP
    0.06
     premiere
    0.06
    _do
    0.06
     finale
    0.06
     bang
    0.06
     articulate
    0.06
    Act Density 0.009%

    No Known Activations