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

    Neuronpedia

    INDEX
    Explanations

    links and URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vase
    0.75
     zacz
    0.73
     gameState
    0.73
     весе
    0.72
     Narrative
    0.72
     figurine
    0.72
     Modifier
    0.70
     Mod
    0.70
     Poem
    0.69
     ja
    0.69
    POSITIVE LOGITS
    hormat
    0.73
    apm
    0.73
    Produto
    0.72
    矯
    0.69
    血糖
    0.69
    hepatic
    0.68
    otid
    0.68
    groupBy
    0.67
    aprend
    0.67
    foils
    0.67
    Act Density 0.023%

    No Known Activations