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

    Neuronpedia

    INDEX
    Explanations

    movie titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     encaps
    -0.07
     outskirts
    -0.07
     Finnish
    -0.06
     Garner
    -0.06
    liğine
    -0.06
     Shak
    -0.06
     čist
    -0.06
     کی
    -0.06
    ливі
    -0.06
     shel
    -0.06
    POSITIVE LOGITS
    ufac
    0.06
     fixes
    0.06
    /update
    0.06
    iolet
    0.06
    ruc
    0.06
    _tar
    0.06
    .Mapping
    0.06
    ovel
    0.06
     انگ
    0.06
    iseconds
    0.06
    Act Density 0.051%

    No Known Activations