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

    Neuronpedia

    INDEX
    Explanations

    overflow hidden

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ẵ
    0.38
    軹
    0.38
     sealer
    0.38
    feas
    0.37
     বিকল্প
    0.37
    樀
    0.36
    lägt
    0.36
    seconds
    0.36
    windowActionBar
    0.36
     enak
    0.36
    POSITIVE LOGITS
     detail
    0.42
     Normalmente
    0.39
     usual
    0.38
     riche
    0.38
     write
    0.37
     unknown
    0.36
     geral
    0.36
     ayuda
    0.36
    Namespace
    0.35
     amorphous
    0.35
    Act Density 0.002%

    No Known Activations