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

    Neuronpedia

    INDEX
    Explanations

    milestone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -fed
    -0.06
    alyzed
    -0.06
    umnos
    -0.06
     přeh
    -0.06
     Pace
    -0.06
     Shim
    -0.06
     nhưng
    -0.06
    larını
    -0.06
     User
    -0.06
     contenu
    -0.06
    POSITIVE LOGITS
    ooter
    0.07
    olar
    0.07
    }_${
    0.06
    าจ
    0.06
    _Game
    0.06
    899
    0.06
     discovers
    0.06
    _THREADS
    0.06
    леж
    0.06
    _________________↵↵
    0.06
    Act Density 0.427%

    No Known Activations