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

    Neuronpedia

    INDEX
    Explanations

    various labels and classifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    󠁥
    0.35
     maneiras
    0.32
     quanta
    0.32
     toNumber
    0.31
     roupas
    0.30
     meus
    0.30
     wagg
    0.30
     multiplets
    0.30
     policías
    0.30
     kinetics
    0.30
    POSITIVE LOGITS
    i
    0.41
    ad
    0.39
    el
    0.38
    the
    0.37
    ed
    0.36
    ↵↵
    0.35
    an
    0.33
    த
    0.32
    and
    0.32
    What
    0.32
    Act Density 0.031%

    No Known Activations