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

    Neuronpedia

    INDEX
    Explanations

    set to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     municipalité
    0.97
     seamlessly
    0.96
     اشاره
    0.92
     thereby
    0.90
    ciano
    0.90
     dikutip
    0.90
    Italie
    0.90
     อ่ะ
    0.89
     protestors
    0.89
    νοντας
    0.88
    POSITIVE LOGITS
    0.86
    గ్ర
    0.79
    ,
    0.76
     Silver
    0.75
     **
    0.72
    :
    0.71
     (
    0.70
    Silver
    0.69
    （
    0.68
     odol
    0.68
    Act Density 0.003%

    No Known Activations