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

    Neuronpedia

    INDEX
    Explanations

    such, which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    exit
    -0.07
    练习
    -0.07
    译
    -0.07
     Enterprises
    -0.07
     Regulations
    -0.07
     reun
    -0.06
    晤
    -0.06
    dbus
    -0.06
    ⇔
    -0.06
     {};
    -0.06
    POSITIVE LOGITS
    /gui
    0.08
     aren
    0.07
     minValue
    0.07
    俅
    0.07
     overriding
    0.07
     Mixing
    0.07
     Kle
    0.07
    DialogContent
    0.07
    _Write
    0.07
     wholly
    0.07
    Act Density 0.099%

    No Known Activations