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

    Neuronpedia

    INDEX
    Explanations

    "a" followed by verbs/nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.20
    ’
    0.19
    /
    0.17
    ,
    0.17
    ch
    0.17
     en
    0.17
    p
    0.16
     es
    0.16
    0
    0.16
     a
    0.16
    POSITIVE LOGITS
    itabbam
    0.16
     |_{
    0.16
     منها
    0.16
     rhinophores
    0.16
    0.16
    𒆳
    0.15
     sparsebundle
    0.15
     DENUMIRE
    0.15
     কহ
    0.15
    Dani
    0.15
    Act Density 0.274%

    No Known Activations