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

    Neuronpedia

    INDEX
    Explanations

    days of the week in dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     afternoon
    0.45
    newtheorem
    0.44
    事は
    0.42
     alterna
    0.42
    च्युअल
    0.41
     সাজ
    0.41
    ('.'
    0.40
    PPtr
    0.40
    पोज
    0.40
    ίζει
    0.39
    POSITIVE LOGITS
    ors
    0.42
    ،
    0.40
     dígitos
    0.38
    ar
    0.38
     Label
    0.38
    şam
    0.38
     Jul
    0.37
    ;
    0.37
    aman
    0.36
    dom
    0.36
    Act Density 0.001%

    No Known Activations