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

    Neuronpedia

    INDEX
    Explanations

    question answering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AE
    -0.07
    (which
    -0.07
     составляет
    -0.07
    _lost
    -0.07
     descriptors
    -0.06
    Fuse
    -0.06
    _ticks
    -0.06
    ONGL
    -0.06
    TickCount
    -0.06
    _prepare
    -0.06
    POSITIVE LOGITS
     Null
    0.07
    ้านด
    0.06
    d
    0.06
     Weld
    0.06
    ChildScrollView
    0.06
    specifier
    0.06
    ану
    0.06
     GOOGLE
    0.06
    <Cell
    0.06
    _jButton
    0.06
    Act Density 0.118%

    No Known Activations