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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     getIndex
    -0.07
    Pont
    -0.06
    718
    -0.06
    sig
    -0.06
    icare
    -0.06
    -data
    -0.06
     notre
    -0.06
     Cad
    -0.06
    -picker
    -0.06
    elez
    -0.06
    POSITIVE LOGITS
    基本
    0.07
     장
    0.07
    .amazon
    0.07
    import
    0.07
     Manufacturers
    0.06
    _normal
    0.06
    lemma
    0.06
    •
    0.06
     crank
    0.06
    _____
    0.06
    Act Density 0.070%

    No Known Activations