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

    Neuronpedia

    INDEX
    Explanations

    control systems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inders
    -0.26
     nâ
    -0.26
     foss
    -0.25
     afford
    -0.25
    åĨľåī¯
    -0.25
    ıl
    -0.25
    untary
    -0.25
     mysterious
    -0.25
     unfamiliar
    -0.24
    ä»»ä½ķæŶåĢĻ
    -0.24
    POSITIVE LOGITS
    ä¸İæѤ
    0.28
    ç®ĢåĮĸ
    0.26
    ä¸Ģæĸ¹
    0.25
    ساÙĨ
    0.25
    -theme
    0.25
     Hubbard
    0.25
    ç²¾
    0.24
    broker
    0.24
    åķĨçĶ¨
    0.24
     broker
    0.24
    Act Density 0.008%

    No Known Activations