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

    Neuronpedia

    INDEX
    Explanations

    tones

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     potencia
    -0.08
     liens
    -0.08
     uomini
    -0.08
     занятий
    -0.08
     निश
    -0.08
     alunos
    -0.08
     Hopefully
    -0.08
     yhtä
    -0.07
     заниматься
    -0.07
     leerlingen
    -0.07
    POSITIVE LOGITS
     emphasizing
    0.10
     tailored
    0.09
    _ENGINE
    0.09
    强调
    0.09
    �
    0.08
     portraying
    0.08
    Aligned
    0.07
    .medium
    0.07
     my
    0.07
     overhaul
    0.07
    Act Density 0.004%

    No Known Activations