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

    Neuronpedia

    INDEX
    Explanations

    citys associated with universities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    certain
    1.33
     is
    1.30
    7
    1.27
    9
    1.24
    s
    1.23
    6
    1.23
    1
    1.17
    poss
    1.16
    เรา
    1.16
     बनर्जी
    1.16
    POSITIVE LOGITS
     linguistique
    1.13
    ｄ
    1.13
    ي
    1.11
     étend
    1.09
    쨰
    1.09
    UTES
    1.08
    ಲ್ಲು
    1.08
    бліоте
    1.06
    вига
    1.05
     smach
    1.05
    Act Density 0.008%

    No Known Activations