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

    Neuronpedia

    INDEX
    Explanations

    all required or turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    con
    0.42
     pand
    0.42
     champ
    0.40
    THUR
    0.39
    胖
    0.39
    fter
    0.38
    Con
    0.37
    mar
    0.37
     br
    0.37
     conno
    0.37
    POSITIVE LOGITS
     birthday
    0.51
     Birthday
    0.51
     address
    0.47
    birthday
    0.46
     phoneNumber
    0.45
     emails
    0.45
     مین
    0.44
    年龄
    0.42
    coordinates
    0.41
     voicemail
    0.41
    Act Density 0.001%

    No Known Activations