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

    Neuronpedia

    INDEX
    Explanations

    Measure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     descent
    -0.09
     antar
    -0.08
     acol
    -0.08
    ént
    -0.07
     Benedict
    -0.07
    ränkt
    -0.07
    614
    -0.07
     Neon
    -0.07
    वाल
    -0.07
    ndash
    -0.07
    POSITIVE LOGITS
     பகுதியில்
    0.09
     హీరో
    0.09
    ouvoir
    0.08
     Lamborghini
    0.08
     freeway
    0.08
     FAILURE
    0.08
    UNIC
    0.08
     initiatief
    0.08
     peliculas
    0.08
     wszyst
    0.08
    Act Density 0.003%

    No Known Activations