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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     транспор
    -0.07
    ा↵↵
    -0.07
    $$$$
    -0.07
    %.↵↵
    -0.07
    sembler
    -0.06
    Segoe
    -0.06
     >>↵↵
    -0.06
    окрем
    -0.06
    这里
    -0.06
    )↵↵
    -0.06
    POSITIVE LOGITS
    λλι
    0.07
     güneş
    0.06
     Construction
    0.06
     revision
    0.06
     onCancel
    0.06
    .fade
    0.06
     notas
    0.06
    ��
    0.06
    baseline
    0.06
     ash
    0.06
    Act Density 0.069%

    No Known Activations