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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (hr
    -0.07
     mh
    -0.07
     indie
    -0.07
     Gram
    -0.06
     ﾘ
    -0.06
    eat
    -0.06
    eree
    -0.06
     COS
    -0.06
     &=
    -0.06
     <->
    -0.06
    POSITIVE LOGITS
     STATUS
    0.06
    lığa
    0.06
     bảng
    0.06
    Activated
    0.06
     článku
    0.06
    。↵
    0.06
    _CONSOLE
    0.06
    contained
    0.06
     Match
    0.06
     Prepare
    0.06
    Act Density 0.025%

    No Known Activations