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

    Neuronpedia

    INDEX
    Explanations

    warranties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bra
    -0.06
    凡
    -0.06
     Джон
    -0.06
     městě
    -0.06
    ０
    -0.06
    計算
    -0.06
    ha
    -0.05
     Bull
    -0.05
    ams
    -0.05
    Prov
    -0.05
    POSITIVE LOGITS
     pedido
    0.08
    becue
    0.07
    respons
    0.07
     attn
    0.07
    invoices
    0.06
    .getClass
    0.06
     Heidi
    0.06
    ・━
    0.06
    總
    0.06
     whatsoever
    0.06
    Act Density 0.001%

    No Known Activations