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

    Neuronpedia

    INDEX
    Explanations

    code structure initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     студен
    1.36
     fornisce
    1.23
    ள்ளதாக
    1.21
     возможность
    1.16
    ంది
    1.15
    ло
    1.13
    नी
    1.12
    تين
    1.11
     требований
    1.10
     utilizar
    1.09
    POSITIVE LOGITS
     and
    1.82
     or
    1.80
     for
    1.75
     to
    1.58
     as
    1.56
     in
    1.52
    ish
    1.50
    in
    1.48
     amidst
    1.44
     on
    1.41
    Act Density 0.126%

    No Known Activations