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

    Neuronpedia

    INDEX
    Explanations

    buy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -functions
    -0.07
     shred
    -0.07
     {↵↵
    -0.06
     full
    -0.06
     distorted
    -0.06
    都
    -0.06
     Including
    -0.06
    ット
    -0.06
     {↵
    -0.06
     shrink
    -0.06
    POSITIVE LOGITS
    _ENDIAN
    0.07
     amat
    0.07
     Marlins
    0.06
    (DWORD
    0.06
     scorer
    0.06
     je
    0.06
     Αυ
    0.06
    ΑΝ
    0.06
    osate
    0.06
     outra
    0.06
    Act Density 0.018%

    No Known Activations