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

    Neuronpedia

    INDEX
    Explanations

    table

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     справи
    -0.08
    Cos
    -0.07
    .lv
    -0.07
    .".
    -0.07
    SharedPtr
    -0.07
    eniz
    -0.06
    _usec
    -0.06
    ignet
    -0.06
    mani
    -0.06
    Milliseconds
    -0.06
    POSITIVE LOGITS
    allax
    0.07
    assertSame
    0.06
     Psalm
    0.06
     many
    0.06
    anooga
    0.06
    capabilities
    0.06
    кет
    0.06
     Catalan
    0.06
    	animation
    0.06
     вра
    0.06
    Act Density 0.001%

    No Known Activations