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
    Division
    -0.07
    ,['
    -0.06
    _Line
    -0.06
    Annual
    -0.06
     ""}↵
    -0.06
    Bin
    -0.06
    ¼
    -0.06
    一人
    -0.06
    Java
    -0.06
    물
    -0.06
    POSITIVE LOGITS
    γρα
    0.07
    ضافة
    0.07
     thịt
    0.07
    peg
    0.06
     turf
    0.06
     transporting
    0.06
     homeland
    0.06
    eyh
    0.06
     감
    0.06
    _and
    0.06
    Act Density 0.000%

    No Known Activations