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

    Neuronpedia

    INDEX
    Explanations

    soul music and food

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alrededores
    -2.25
    ⩴
    -2.11
     olvidar
    -2.06
     intentando
    -2.02
     perlindungan
    -2.00
     hiciera
    -2.00
    稣
    -1.98
     sabias
    -1.97
    -1.94
    饪
    -1.93
    POSITIVE LOGITS
    2.52
    '
    2.44
    <bos>
    2.02
    }
    1.92
    L
    1.91
    )
    1.89
    また
    1.88
    </h2>
    1.88
    新年
    1.87
    または
    1.86
    Act Density 0.006%
    No Known Activations