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

    Neuronpedia

    INDEX
    Explanations

    adding or including

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     flusso
    0.89
     appartamento
    0.84
     regelmäßig
    0.83
     cellulaire
    0.82
     volontà
    0.82
     regelmatig
    0.82
     rež
    0.81
     pretože
    0.81
     antigo
    0.80
    étrique
    0.80
    POSITIVE LOGITS
    р
    0.88
    л
    0.85
    س
    0.84
    itarian
    0.83
     Bangladeshi
    0.78
     Bangladesh
    0.77
     landowner
    0.75
    納税
    0.73
    נ
    0.72
    嚓
    0.72
    Act Density 0.001%

    No Known Activations