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

    Neuronpedia

    INDEX
    Explanations

    humanity and life

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    т
    1.64
    il
    1.59
    ం
    1.44
    ı
    1.39
    ის
    1.28
    ます
    1.27
    ни
    1.25
    á
    1.23
    ิ
    1.23
    й
    1.22
    POSITIVE LOGITS
     japonais
    1.35
     magasins
    1.30
     humains
    1.30
     doubtless
    1.27
     siècles
    1.27
     geographies
    1.26
     umani
    1.25
     titans
    1.25
     philanthrop
    1.24
     וע
    1.24
    Act Density 0.734%

    No Known Activations