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

    Neuronpedia

    INDEX
    Explanations

    specific common nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     అమలు
    0.35
    驄
    0.35
     ಸ್ವಲ್ಪ
    0.33
     ඉතා
    0.33
    本作
    0.33
     വളരെ
    0.33
     dość
    0.33
    వన్
    0.32
     codebase
    0.32
    പര
    0.32
    POSITIVE LOGITS
     of
    0.47
     from
    0.47
     that
    0.44
    、
    0.44
     and
    0.41
     at
    0.39
    that
    0.38
     for
    0.38
     whose
    0.36
     on
    0.36
    Act Density 0.049%

    No Known Activations