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

    Neuronpedia

    INDEX
    Explanations

    page numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HE
    0.44
    one
    0.43
    he
    0.43
    E
    0.43
    alar
    0.42
    F
    0.42
    name
    0.42
    fact
    0.42
    ia
    0.41
    RA
    0.41
    POSITIVE LOGITS
     chiens
    0.51
    ្សា
    0.49
     projets
    0.46
     chantier
    0.45
     terrains
    0.45
     chatId
    0.44
     nœ
    0.43
    🔫
    0.43
     libid
    0.43
     détect
    0.43
    Act Density 0.002%

    No Known Activations