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

    Neuronpedia

    INDEX
    Explanations

    best

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sailors
    -0.07
     sailor
    -0.07
    monkey
    -0.06
    Joint
    -0.06
    conomy
    -0.06
    .Array
    -0.06
    ानद
    -0.06
     gadget
    -0.06
     слив
    -0.06
     damaging
    -0.06
    POSITIVE LOGITS
    ).
↵
    0.07
    へと
    0.07
    _cast
    0.07
    (_,
    0.07
     Best
    0.06
     defy
    0.06
     wr
    0.06
     <=>
    0.06
     (%)
    0.06
    .GetResponse
    0.06
    Act Density 0.007%

    No Known Activations