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

    Neuronpedia

    INDEX
    Explanations

    /res

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ()).
    -0.07
     ideas
    -0.07
    .UTF
    -0.06
     cray
    -0.06
    These
    -0.06
    Pressed
    -0.06
     GAP
    -0.06
     combinations
    -0.06
    -carousel
    -0.06
    <Character
    -0.06
    POSITIVE LOGITS
    ynchronize
    0.07
    uniq
    0.07
    мент
    0.06
    _RW
    0.06
     sprayed
    0.06
    amen
    0.06
    €
    0.06
    Portable
    0.06
    cco
    0.06
     Soy
    0.06
    Act Density 0.000%

    No Known Activations