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

    Neuronpedia

    INDEX
    Explanations

    iline

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    892
    -0.07
    _under
    -0.07
     Atlantis
    -0.07
     metrů
    -0.07
     mour
    -0.06
    절
    -0.06
     включа
    -0.06
    @endforeach
    -0.06
     palabras
    -0.06
    isiert
    -0.06
    POSITIVE LOGITS
     routes
    0.07
    )\<
    0.07
    hg
    0.07
    iline
    0.06
    Assistant
    0.06
    .G
    0.06
     async
    0.06
    Inicial
    0.06
     binds
    0.06
     assignment
    0.06
    Act Density 0.002%

    No Known Activations