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

    Neuronpedia

    INDEX
    Explanations

    green sustainability initiatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    0.91
    t
    0.87
    l
    0.84
    }
    0.80
    a
    0.76
    j
    0.75
    that
    0.71
    it
    0.70
    )
    0.70
    glacial
    0.68
    POSITIVE LOGITS
    isasi
    0.65
     existente
    0.63
     схе
    0.62
     aparece
    0.61
     Banca
    0.60
     iniziale
    0.60
     Hotels
    0.59
     arquivos
    0.59
     amerik
    0.59
     direta
    0.59
    Act Density 0.003%

    No Known Activations