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

    Neuronpedia

    INDEX
    Explanations

    flow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dbus
    -0.07
    imag
    -0.06
    окс
    -0.06
     seam
    -0.06
    ियन
    -0.06
    >())
    -0.06
    胶
    -0.06
    .getChannel
    -0.06
    ]=='
    -0.06
    슨
    -0.06
    POSITIVE LOGITS
     TASK
    0.07
    basic
    0.07
     motivating
    0.07
    VERBOSE
    0.06
     فرمان
    0.06
    .Ş
    0.06
    _gps
    0.06
    .ERR
    0.06
     Msg
    0.06
    Slinky
    0.06
    Act Density 0.007%

    No Known Activations