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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,),↵
    -0.06
     fabrics
    -0.06
    四
    -0.06
    ,Q
    -0.06
     дорож
    -0.06
     digitally
    -0.06
     střed
    -0.06
    Linear
    -0.06
    _TRACK
    -0.06
     Sid
    -0.06
    POSITIVE LOGITS
    Inlining
    0.08
    HOST
    0.07
     newList
    0.07
    amura
    0.07
    /TT
    0.06
    (parsed
    0.06
     Titans
    0.06
    Whether
    0.06
     관리자
    0.06
    (actor
    0.06
    Act Density 0.001%

    No Known Activations