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

    Neuronpedia

    INDEX
    Explanations

    Winning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pur
    -0.07
    주의
    -0.06
    求购
    -0.06
     bian
    -0.06
    YRO
    -0.06
    -cor
    -0.06
     bombard
    -0.06
    η
    -0.06
    ٤
    -0.06
    vd
    -0.06
    POSITIVE LOGITS
    HLT
    0.07
     (;;)
    0.06
    assertCount
    0.06
     sqlSession
    0.06
    Wel
    0.06
    lü
    0.06
     Elves
    0.06
    _epsilon
    0.06
    rgctx
    0.06
    andır
    0.06
    Act Density 0.022%

    No Known Activations