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

    Neuronpedia

    INDEX
    Explanations

    Incompatibility

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    全文
    -0.07
     sher
    -0.07
    �
    -0.07
     LU
    -0.07
     Rom
    -0.07
     Shack
    -0.07
    SPATH
    -0.07
     crud
    -0.07
     jo
    -0.06
    她说
    -0.06
    POSITIVE LOGITS
     стоит
    0.08
     opinion
    0.07
     случай
    0.07
     uneven
    0.07
     sizeof
    0.07
     morphology
    0.07
    安防
    0.07
    _LAYOUT
    0.06
    舆论
    0.06
    _OC
    0.06
    Act Density 0.128%

    No Known Activations