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

    Neuronpedia

    INDEX
    Explanations

    under

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Morales
    -0.07
    ﱭ
    -0.07
     rooftop
    -0.07
     Greenville
    -0.07
    TRACE
    -0.06
     Released
    -0.06
    言
    -0.06
    优化
    -0.06
     MPI
    -0.06
     האחרונות
    -0.06
    POSITIVE LOGITS
     insect
    0.07
    sofar
    0.07
     Where
    0.07
    .cwd
    0.07
    _SECRET
    0.06
     det
    0.06
     çeş
    0.06
     cort
    0.06
    whereIn
    0.06
    �
    0.06
    Act Density 0.015%

    No Known Activations