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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >No
    -0.07
     Walker
    -0.07
    atím
    -0.07
    expects
    -0.07
    *******
    -0.06
    _EXPECT
    -0.06
    workspace
    -0.06
    _partner
    -0.06
    page
    -0.06
    dığını
    -0.06
    POSITIVE LOGITS
    BITS
    0.07
     accum
    0.07
     白
    0.07
     Enlightenment
    0.07
     instituted
    0.07
     Animation
    0.07
     И
    0.06
     Throw
    0.06
    lag
    0.06
     chí
    0.06
    Act Density 0.016%

    No Known Activations