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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    0.55
     this
    0.47
     a
    0.46
     one
    0.45
    .
    0.44
    ,
    0.43
     your
    0.41
     some
    0.40
     an
    0.39
     our
    0.38
    POSITIVE LOGITS
    equivariant
    0.33
     بتساوي
    0.33
     Trebuie
    0.32
    থাৎ
    0.32
    覤
    0.32
     دستیاب
    0.31
    🉑
    0.31
    Ų
    0.31
     Actualmente
    0.30
    zovaniyu
    0.30
    Act Density 0.051%

    No Known Activations