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

    Neuronpedia

    INDEX
    Explanations

    card transactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     notValid
    0.44
     همیشه
    0.40
     सूट
    0.38
     সেখানে
    0.37
    大师
    0.37
     çıktı
    0.37
     вий
    0.36
     illusory
    0.36
     বারবার
    0.36
     revisiting
    0.36
    POSITIVE LOGITS
     access
    0.42
    new
    0.39
    net
    0.37
    iprocal
    0.37
    area
    0.36
    tad
    0.36
    نو
    0.36
    憩
    0.35
     directions
    0.35
    access
    0.35
    Act Density 0.000%

    No Known Activations