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

    Neuronpedia

    INDEX
    Explanations

    "ID" explanations or definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     –
    0.44
    t
    0.42
    ,
    0.42
     والد
    0.40
    ત
    0.40
    τερα
    0.40
    ációs
    0.39
     >>
    0.39
     puis
    0.38
     boyfriend
    0.38
    POSITIVE LOGITS
     mignon
    0.51
     ciekaw
    0.51
     atta
    0.48
    ফান
    0.48
    唳
    0.47
    蹼
    0.47
     Ondo
    0.46
    Prothorax
    0.46
     ወቅ
    0.46
     Rostov
    0.46
    Act Density 0.001%

    No Known Activations