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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     submodule
    -0.08
    ６
    -0.07
    dbus
    -0.06
    ]%
    -0.06
    .getId
    -0.06
    (pp
    -0.06
    .rstrip
    -0.06
     datasets
    -0.06
    _slug
    -0.06
    Comple
    -0.06
    POSITIVE LOGITS
     Rei
    0.07
    ителя
    0.06
    ارس
    0.06
     DI
    0.06
     doma
    0.06
    _DEC
    0.06
    _MC
    0.06
    _mtx
    0.06
    _orient
    0.06
    .bounds
    0.06
    Act Density 0.042%

    No Known Activations