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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (sync
    -0.06
     Cock
    -0.06
     คร
    -0.06
    (cur
    -0.06
    RIEND
    -0.06
    -rich
    -0.06
     Burn
    -0.06
     sensible
    -0.06
     sel
    -0.06
    subjects
    -0.05
    POSITIVE LOGITS
     Pedido
    0.07
     Femme
    0.06
    몬
    0.06
    itespace
    0.06
     rozum
    0.06
    括
    0.06
     phá
    0.06
     квар
    0.06
    düm
    0.06
    罗
    0.06
    Act Density 0.155%

    No Known Activations