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

    Neuronpedia

    INDEX
    Explanations

    introduction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aur
    -0.07
    iever
    -0.06
     однако
    -0.06
    ?-
    -0.06
     MessageBoxIcon
    -0.06
     jusqu
    -0.06
     rocked
    -0.06
    SPAN
    -0.06
    tical
    -0.06
    cdnjs
    -0.06
    POSITIVE LOGITS
     what
    0.07
     里
    0.07
     conducting
    0.06
    탄
    0.06
    Classic
    0.06
     Generally
    0.06
    rial
    0.06
     tutor
    0.06
     Smile
    0.06
     هست
    0.06
    Act Density 0.003%

    No Known Activations