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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,params
    -0.28
    lö
    -0.25
    åĽ°
    -0.25
    ="/">
    -0.25
    çľ¼éķľ
    -0.25
     Guinness
    -0.24
    testdata
    -0.24
     sig
    -0.24
    é³Ķ
    -0.24
    '+↵
    -0.24
    POSITIVE LOGITS
    è°©
    0.28
    BU
    0.26
     AMS
    0.25
    Mos
    0.25
    caf
    0.25
    (children
    0.25
    lav
    0.25
     Mos
    0.25
     continu
    0.24
    羨
    0.24
    Act Density 0.253%

    No Known Activations