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

    Neuronpedia

    INDEX
    Explanations

    llama

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uncertainties
    -0.07
    TED
    -0.07
    θεί
    -0.06
    ович
    -0.06
     уж
    -0.06
    imited
    -0.06
    设置
    -0.06
     butterknife
    -0.06
    ("").
    -0.06
     sung
    -0.06
    POSITIVE LOGITS
    <Form
    0.07
    (year
    0.07
     Q
    0.07
    (listener
    0.06
     elabor
    0.06
    hue
    0.06
     sla
    0.06
    <Article
    0.06
     Small
    0.06
     PLA
    0.06
    Act Density 0.004%

    No Known Activations