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

    Neuronpedia

    INDEX
    Explanations

    Discarding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     чего
    -0.07
    .yy
    -0.07
     děl
    -0.07
    _of
    -0.06
     코
    -0.06
    ควร
    -0.06
     bree
    -0.06
    iden
    -0.06
    まる
    -0.06
     CSC
    -0.06
    POSITIVE LOGITS
    undreds
    0.07
     lifelong
    0.07
     TInt
    0.07
    elong
    0.06
     tentative
    0.06
    (Database
    0.06
     newVal
    0.06
    epoch
    0.06
    (border
    0.06
     fearing
    0.06
    Act Density 0.008%

    No Known Activations