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

    Neuronpedia

    INDEX
    Explanations

    Due Diligence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Asw
    0.73
    ahassee
    0.73
    oxone
    0.70
     Sonn
    0.70
    ෘ
    0.69
    शहर
    0.67
    azada
    0.67
     mercy
    0.66
     ratus
    0.66
    azines
    0.65
    POSITIVE LOGITS
    имо
    0.59
    查询
    0.57
     इंजी
    0.51
     Inquiry
    0.51
    query
    0.50
     খাবার
    0.50
     query
    0.49
     enquiry
    0.49
    En
    0.49
     जाट
    0.49
    Act Density 0.239%

    No Known Activations